Article(id=1325533078244049270, tenantId=1146029695717560320, journalId=1256213402557890569, issueId=1325531848021140417, articleNumber=null, orderNo=null, doi=10.16835/j.cnki.1000-9817.2025323, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1753977600000, receivedDateStr=2025-08-01, revisedDate=1757174400000, revisedDateStr=2025-09-07, acceptedDate=null, acceptedDateStr=null, onlineDate=1793961313067, onlineDateStr=2026-11-06, pubDate=1764000000000, pubDateStr=2025-11-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793961313067, onlineIssueDateStr=2026-11-06, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793961313067, creator=13701087609, updateTime=1793961313067, updator=13701087609, issue=Issue{id=1325531848021140417, tenantId=1146029695717560320, journalId=1256213402557890569, year='2025', volume='46', issue='11', pageStart='1521', pageEnd='1672', issueExtLink='null', onlineDate='null', pubDate='1764000000000', pubDateStr='2025-11-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793961019759, creator='13701087609', updateTime=1793961019759, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=1584, endPage=1589, ext={EN=ArticleExt(id=1325533087547015543, articleId=1325533078244049270, tenantId=1146029695717560320, journalId=1256213402557890569, language=EN, title=Prediction model for the risk of social network addiction among college students based on multi-algorithm machine learning approaches, columnId=1259565855189418448, journalTitle=Chinese Journal of School Health, columnName=Mental Health, runingTitle=null, highlight=null, articleAbstract=
Objective

To develop multiple machine learning models to identify college students at high risk of social network addiction (SNA) and to select key predictors, so as to provide evidences for tiered screening and interventions.

Methods

A multi-stage cluster sampling was conducted among 12 541 undergraduates at five universities in Guizhou Province from September to October 2024. The Chinese version of Social Networking Addiction Scale (SNAS-C) was used to classify high-risk individuals. Candidate variables included demographic characteristics, the total scores of Adult ADHD Self-report Scale (ASRS) and the Chinese version of Diagnostic and Statistical Manual of Mental Disorders, 5th Edition Self-rated level 1 Cross-cutting Symptom Measure (DSM-5 CCSM), academic stress and academic satisfaction and 24-hour Movement Guidelines. Four machine learning models including multilayer perceptron neural network (MLP), XGBoost, K-nearest neighbors (KNN), and gradient boosting decision trees (GBDT) were trained with an 8∶2 train-test split. Model performance was evaluated using accuracy, recall, F1 score, and the area under the ROC curve (AUC), followed by feature importance analysis.

Results

The detection rate of high-risk SNA was 8.60%, higher in girls (10.10%) than boys (6.74%), with a statistically significant difference (χ2=44.42, P < 0.01). Compared with the low-risk group for SNA, the high-risk group had higher ASRS scores, more severe of depression and anxiety, greater academic stress, and lower academic satisfaction (t=-21.23, -16.12, -16.73, -13.81, 11.58, all P < 0.01). Regarding 24-hour movement behaviors (physical activity, sleep, sedentary/screen time), the high-risk SNA group showed lower compliance rates (11.77%, 5.65%, 57.92%) than the low-risk group (15.57%, 13.16%, 75.32%) (χ2=11.04, 50.72, 154.40, all P < 0.01). All four models demonstrated good discrimination; XGBoost performed the best (accuracy 88.18%, F1=0.881), while KNN achieved the highest AUC (0.90). Feature importance analysis indicated ASRS as the most critical predictor of SNA, followed by academic stress, depression, age, and academic satisfaction.

Conclusions

Machine learning models can effectively identify college students at high risk for SNA. ADHD symptoms, internalizing problems, and academic stress are major risk factors, while 24-hour movement behaviors are key intervention targets, especially sleep and screen time.

, authors=Lin LUO, authorsList=Lin LUO, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright ©2025 Chinese Journal of School Health. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1325533099232346491, articleId=1325533078244049270, tenantId=1146029695717560320, journalId=1256213402557890569, language=CN, title=基于多算法机器学习的大学生社交网络成瘾风险预测模型, columnId=1259565858817491410, journalTitle=中国学校卫生, columnName=心理卫生, runingTitle=null, highlight=null, articleAbstract=
目的

构建多种机器学习模型识别大学生社交网络成瘾(SNA)高风险个体,筛选关键预测因子,为精准筛查与干预提供循证依据。

方法

于2024年9—10月,采用多阶段整群抽样抽取贵州省某大学城5所高校12 541名本科生为对象,采用中文版社交网络成瘾量表(SNAS-C)、成人注意缺陷/多动障碍自评量表(ASRS)、《精神疾病诊断与统计手册第五版》自评水平1横切症状测量-成人中文版(DSM-5 CCSM)、学业压力与学业满意度问卷,以及24 h活动指南进行问卷调查。采用多层感知机神经网络(MLP)、XGBoost、K近邻(KNN)和梯度提升决策树(GBDT)4种机器学习模型,按8∶2划分训练集与测试集,利用准确率、召回率、F1值和ROC曲线下面积(AUC)评估模型性能,并进一步开展特征重要性分析。

结果

SNA高风险检出率为8.60%,女生(10.10%)高于男生(6.74%),差异有统计学意义(χ2=44.42,P < 0.01)。相比SNA低风险组,高风险组ASRS得分更高,抑郁、焦虑等更严重,学业压力更大、满意度更低(t值分别为-21.23,-16.12,-16.73,-13.81,11.58,P值均 < 0.01)。在24 h活动行为中(身体活动、睡眠、久坐/屏幕时间),SNA高风险组达标率(11.77%,5.65%,57.92%)相比低风险组(15.57%,13.16%,75.32%)偏低(χ2值分别为11.04,50.72,154.40,P值均 < 0.01)。4种模型均具良好区分度,其中XGBoost表现最佳(准确率88.18%,F1=0.881),KNN的AUC最高(0.90)。特征重要性分析显示ASRS为SNA最关键预测因子,其次为学业压力、抑郁、年龄和学业满意度。

结论

机器学习模型可有效识别大学生SNA高风险个体;注意缺陷症状、内化问题和学业压力是主要风险因素,24 h活动行为(尤其睡眠与屏幕时间)为关键干预靶点。

, authors=罗琳, authorsList=罗琳, authorCompany=null, correspAuthors=null, authorNote=

罗琳(1979-),女,贵州贵阳人,博士,教授,主要研究方向为体育健康传播与健康教育

, correspAuthorsNote=null, copyrightStatement=版权所有©《中国学校卫生》编辑部2025, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=YD+cfm1sAxzns1HYCUXAYw==, magXml=2c4LLuDCgfA4++nd+eGolw==, pdfUrl=null, pdf=3EXEe7sKa8Lx+aO/PNzmOQ==, pdfFileSize=1133112, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=EtEqTaZCxPddd2xbmFc1PA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=sEQ14Km857wduDFEsAvyvA==, mapNumber=null, fund=null)}, authors=[Author(id=1325533104273899904, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325533105024680322, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, authorId=1325533104273899904, language=EN, stringName=Lin LUO, firstName=Lin, middleName=null, lastName=LUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Physical Education, Guizhou Normal University/Key Laboratory of Brain Function and Brain Disease Prevention and Treatment of Guizhou Province, Guiyang 550025, Guizhou Province, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325533107239272835, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, authorId=1325533104273899904, language=CN, stringName=罗琳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025, bio={"content":"

罗琳(1979-),女,贵州贵阳人,博士,教授,主要研究方向为体育健康传播与健康教育

"}, bioImg=null, bioContent=

罗琳(1979-),女,贵州贵阳人,博士,教授,主要研究方向为体育健康传播与健康教育

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325533103443427708, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, xref=null, ext=[AuthorCompanyExt(id=1325533103456010621, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, companyId=1325533103443427708, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Physical Education, Guizhou Normal University/Key Laboratory of Brain Function and Brain Disease Prevention and Treatment of Guizhou Province, Guiyang 550025, Guizhou Province, China), AuthorCompanyExt(id=1325533103472787838, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, companyId=1325533103443427708, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025)])])], keywords=[Keyword(id=1325533109290287492, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, orderNo=1, keyword=Communication), Keyword(id=1325533111039312261, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, orderNo=2, keyword=Internet), Keyword(id=1325533111844618630, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, orderNo=3, keyword=Behavior, addictive), Keyword(id=1325533112595399047, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, orderNo=4, keyword=Mental health), Keyword(id=1325533113153241480, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, orderNo=5, keyword=Students), Keyword(id=1325533113828524425, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, orderNo=1, keyword=信息交流), Keyword(id=1325533114646413706, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, orderNo=2, keyword=因特网), Keyword(id=1325533115179090316, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, orderNo=3, keyword=行为,成瘾), Keyword(id=1325533116873589133, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, orderNo=4, keyword=精神卫生), Keyword(id=1325533117645341070, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, orderNo=5, keyword=学生)], refs=[Reference(id=1325533134846181781, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=BUCTOT D B, KIM N, KIM J J. Factors associated with smartphone addiction prevalence and its predictive capacity for health-related quality of life among Filipino adolescents[J]. Child Youth Serv Rev, 2020, 110: 104758., articleTitle=null, refAbstract=null), Reference(id=1325533135244640662, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=KUSS D, GRIFFITHS M. Social networking sites and addiction: ten lessons learned[J]. Int J Environ Res Public Health, 2017, 14(3): 311., articleTitle=null, refAbstract=null), Reference(id=1325533135789900183, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=YU A Y, TIAN S W, VOGEL D, et al. Can learning be virtually boosted? An investigation of online social networking impacts[J]. Comput Educ, 2010, 55(4): 1494-1503., articleTitle=null, refAbstract=null), Reference(id=1325533137471816088, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=YIN H, SHI L. Which type of interpersonal interaction better facilitates college student learning and development in China: face-to-face or online?[J]. ECNU Rev Educ, 2021, 5(1): 9-36., articleTitle=null, refAbstract=null), Reference(id=1325533137836720537, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=BI S, YUAN J, LUO L. The Social Networking Addiction Scale: tran-slation and validation study among Chinese college students[J]. Int J Ment Health Promot, 2024, 26: 51-60., articleTitle=null, refAbstract=null), Reference(id=1325533139057263002, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=MACHIMBARRENA J M, GONZÁLEZ-CABRERA J, ORTEGA-BA-RÓN J, et al. Profiles of problematic Internet use and its impact on adolescents' health-related quality of life[J]. Int J Environ Res Public Health, 2019, 16(20). DOI: 10.3390/ijerph16203877., articleTitle=null, refAbstract=null), Reference(id=1325533139476693403, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU R, XIA D, YIN Y, et al. Analyzing the impact of the Internet on higher education[J]. Int J Secur Appl, 2016, 10(6): 341-350., articleTitle=null, refAbstract=null), Reference(id=1325533139858375068, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=HOU Y, XIONG D, JIANG T, et al. Social media addiction: its impact, mediation, and intervention[J]. Cyberpsychology, 2019, 13(1): 1-17., articleTitle=null, refAbstract=null), Reference(id=1325533140252639645, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=SUN Y, ZHANG Y. A review of theories and models applied in studies of social media addiction and implications for future research[J]. Addict Behav, 2021, 114: 106699., articleTitle=null, refAbstract=null), Reference(id=1325533141926166942, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=GRIFFITHS M D, KUSS D. Adolescent social media addiction (revisited)[J]. Educ Health, 2017, 35(3): 49-52., articleTitle=null, refAbstract=null), Reference(id=1325533142433677727, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=CHENG C, LAU Y C, CHAN L, et al. Prevalence of social media addiction across 32 nations: Meta-analysis with subgroup analysis of classification schemes and cultural values[J]. Addict Behav, 2021, 117: 106845., articleTitle=null, refAbstract=null), Reference(id=1325533144912511392, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=DUMITRESCU M, DUMITRESCU N, TURLIUC S. The social media addiction: what have we learned so far?-a review[J]. BRAIN Broad Res Artif Intell Neurosci, 2023, 14(1): 117-137., articleTitle=null, refAbstract=null), Reference(id=1325533146518929825, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN B, LIU F, DING S, et al. Gender differences in factors associated with smartphone addiction: a cross-sectional study among medical college students[J]. BMC Psychiatry, 2017, 17(1): 341., articleTitle=null, refAbstract=null), Reference(id=1325533146686701986, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=CIMADEVILLA R, JENARO C. Impact on psychological health of Internet and mobile phone abuse in a Spanish sample of secondary students[J]. Revist Argent De Clínic Psicol, 2019, 28(3): 339-347., articleTitle=null, refAbstract=null), Reference(id=1325533147374567843, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=BISCHOF-KASTNER C, KUNTSCHE E, WOLSTEIN J. Identifying problematic Internet users: development and validation of the Internet Motive Questionnaire for Adolescents (IMQ-A)[J]. J Med Internet Res, 2014, 16(10): e230., articleTitle=null, refAbstract=null), Reference(id=1325533149471719844, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=BRANLEY D B, COVEY J. Risky behavior via social media: the role of reasoned and social reactive pathways[J]. Comput Hum Behav, 2018, 78: 183-191., articleTitle=null, refAbstract=null), Reference(id=1325533151191384485, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=LACONI S, KALISZEWSKA-CZEREMSKA K, GNISCI A, et al. Cross-cultural study of problematic Internet use in nine European countries[J]. Comput Hum Behav, 2018, 84: 430-440., articleTitle=null, refAbstract=null), Reference(id=1325533151619203494, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=JORDAN M I, MITCHELL T M. Machine learning: trends, perspectives, and prospects[J]. Science, 2015, 349(6245): 255-260., articleTitle=null, refAbstract=null), Reference(id=1325533152147685799, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO L, YUAN J, WU C, et al. Predictors of depression among Chinese college students: a machine learning approach[J]. BMC Public Health, 2025, 25(1): 470., articleTitle=null, refAbstract=null), Reference(id=1325533153271759272, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=SHAHNAWAZ M G, REHMAN U. Social Networking Addiction Scale[J]. Cogent Psychol, 2020, 7: 1832032., articleTitle=null, refAbstract=null), Reference(id=1325533155440214441, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO L, YUAN J, WANG Y, et al. Possible classifications of social network addiction: a latent profile analysis of Chinese college students[J]. Int J Ment Health Promot, 2025, 27(6): 863-876., articleTitle=null, refAbstract=null), Reference(id=1325533156144857514, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=KESSLER R C, ADLER L, AMES M, et al. The World Health Organization Adult ADHD Self-report Scale (ASRS): a short screening scale for use in the general population[J]. Psychol Med, 2005, 35(2): 245-256., articleTitle=null, refAbstract=null), Reference(id=1325533156304241067, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO L, YUAN J, XU C, et al. Mental health issues and 24-hour movement guidelines-based intervention strategies for university students with high-risk social network addiction: cross-sectional study using a machine learning approach[J]. J Med Internet Res, 2025, 27: e72260., articleTitle=null, refAbstract=null), Reference(id=1325533157075993004, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=陈琳, 许诗玮, 罗学荣. 长沙市大学生注意缺陷多动障碍及影响因素[J]. 中国学校卫生, 2020, 41(12): 1856-1858, 1862., articleTitle=null, refAbstract=null), Reference(id=1325533157591892397, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=CHEN L, XU S W, LUO X R. Prevalence and risk factors of attention deficit hyperactivity disorder among college students in Changsha[J]. Chin J Sch Health, 2020, 41(12): 1856-1858, 1862. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1325533160024588718, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=BRAVO A J, PEARSON M R, STEVENS L E. The DSM-5 self-rated level 1 cross-cutting symptom measure: psychometric properties and associations with alcohol use and related outcomes[J]. J Substance Abuse Treatment, 2018, 94: 1-7., articleTitle=null, refAbstract=null), Reference(id=1325533160418853296, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=MA Y, LI W, WANG X. Psychometric properties of the DSM-5 self-rated level 1 cross-cutting symptom measure in Chinese adults[J]. J Affect Disord, 2021, 282: 1236-1243., articleTitle=null, refAbstract=null), Reference(id=1325533161094136241, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=COHEN S, KAMARCK T, MERMELSTEIN R. A global measure of perceived stress[J]. J Health Soc Behav, 1983, 24(4): 385-396., articleTitle=null, refAbstract=null), Reference(id=1325533161366766002, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=DIENER E, EMMONS R A, LARSEN R J, et al. The satisfaction with life scale[J]. J Pers Assess, 1985, 49(1): 71-75., articleTitle=null, refAbstract=null), Reference(id=1325533162012688819, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=TREMBLAY M S, CARSON V, CHAPUT J P. Introduction to the Canadian 24-hour movement guidelines for children and youth: an integration of physical activity, sedentary behaviour, and sleep[J]. Appl Physiol Nutr Metab, 2016, 41(6 Suppl 3): Ⅲ-Ⅳ., articleTitle=null, refAbstract=null), Reference(id=1325533162964795828, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO L. 24-h movement behaviors and visual impairment among Chinese adolescents with and without obesity[J]. Compl Ther Clin Pract, 2024, 54: 101823., articleTitle=null, refAbstract=null), Reference(id=1325533164604768693, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO L, CAO Y, HU Y, et al. The associations between meeting 24-hour movement guidelines (24-HMG) and self-rated physical and mental health in older adults: cross sectional evidence from China[J]. Int J Environ Res Public Health, 2022, 19(20): 3407., articleTitle=null, refAbstract=null), Reference(id=1325533165556875702, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO L, ZENG X, CAO Y, et al. The associations between meeting 24-hour movement guidelines (24-HMG) and mental health in adolescents: cross sectional evidence from China[J]. Int J Environ Res Public Health, 2023, 20(4): 3167., articleTitle=null, refAbstract=null), Reference(id=1325533168853598647, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=DUC T Q, CHI V T Q, HUYEN N T H, et al. Growing propensity of Internet addiction among Asian college students: Meta-analysis of pooled prevalence from 39 studies with over 50 000 participants[J]. Public Health, 2024, 227: 250-258., articleTitle=null, refAbstract=null), Reference(id=1325533169314972088, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=LEÓN MÉNDEZ M, PADRÓN I, FUMERO A, et al. Effects of Internet and smartphone addiction on cognitive control in adolescents and young adults: a systematic review of fMRI studies[J]. Neurosci Biobehav Rev, 2024, 159: 105572., articleTitle=null, refAbstract=null), Reference(id=1325533170460017081, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=KENDLER K S, GARDNER C O. Sex differences in the pathways to major depression: a study of opposite-sex twin pairs[J]. Am J Psychiatry, 2014, 171(4): 426-435., articleTitle=null, refAbstract=null), Reference(id=1325533171017859514, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU W, YAN Z, ZHANG L. A comparative study of 11 non-linear regression models highlighting autoencoder, DBN, and SVR, enhanced by SHAP importance analysis in soybean branching prediction[J]. Sci Rep, 2024, 14(1): 5905., articleTitle=null, refAbstract=null), Reference(id=1325533171705725371, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=SUN Y, LI Z, LI X, et al. Classifier selection and ensemble model for multi-class imbalance learning in education grants prediction[J]. Appl Artif Intell, 2021, 35(4): 290-303., articleTitle=null, refAbstract=null), Reference(id=1325533174209724860, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=GURJAR S, PATIL C, SURYAWANSHI R, et al. Mental health prediction using machine learning[J]. Internl Res J Engineer Technol, 2022, 9(5): 2395-0056., articleTitle=null, refAbstract=null), Reference(id=1325533175224746429, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=SARIYSKA R, REUTER M, LACHMANN B, et al. Attention deficit/hyperactivity disorder is a better predictor for problematic Internet use than depressione: evidence from Germany[J]. J Addiction Research Therapy, 2015, 6(209): 1-6., articleTitle=null, refAbstract=null), Reference(id=1325533176361402814, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=TANG J, YU Y, DU Y, et al. Prevalence of Internet addiction and its association with stressful life events and psychological symptoms among adolescent Internet users[J]. Addict Behav, 2014, 39(3): 744-747., articleTitle=null, refAbstract=null), Reference(id=1325533178521469375, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=BRAND M, YOUNG K S, LAIER C. Prefrontal control and Internet addiction: a theoretical model and review of neuropsychological and neuroimaging findings[J]. Front Hum Neurosci, 2014, 8: 375., articleTitle=null, refAbstract=null), Reference(id=1325533179356135872, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=DONG G, POTENZA M N. A cognitive-behavioral model of Internet gaming disorder: theoretical underpinnings and clinical implications[J]. J Psychiatr Res, 2014, 58: 7-11., articleTitle=null, refAbstract=null), Reference(id=1325533180576678337, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=ALIMORADI Z, LIN C Y, BROSTRÖM A, et al. Internet addiction and sleep problems: a systematic review and Meta-analysis[J]. Sleep Med Rev, 2019, 47: 51-61., articleTitle=null, refAbstract=null), Reference(id=1325533182719967682, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=WINKLER A, DÖRSING B, RIEF W, et al. Treatment of Internet addiction: a Meta-analysis[J]. Clin Psychol Rev, 2013, 33(2): 317-329., articleTitle=null, refAbstract=null), Reference(id=1325533183596577219, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=SHEN X, WANG C, CHEN C, et al. Stress and Internet addiction: mediated by anxiety and moderated by self-control[J]. Psychol Res Behav Manag, 2023, 16: 1975-1986., articleTitle=null, refAbstract=null)], funds=[Fund(id=1325533132782584212, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, awardId=null, language=CN, fundingSource=国家自然科学基金项目(72364006);贵州省科技计划项目(黔科合基础-ZK[2023]一般251), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1325533103443427708, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, xref=null, ext=[AuthorCompanyExt(id=1325533103456010621, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, companyId=1325533103443427708, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Physical Education, Guizhou Normal University/Key Laboratory of Brain Function and Brain Disease Prevention and Treatment of Guizhou Province, Guiyang 550025, Guizhou Province, China), AuthorCompanyExt(id=1325533103472787838, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, companyId=1325533103443427708, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025)])], figs=[ArticleFig(id=1325533120908509583, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, label=Fig.1, caption=Feature importance gradients for a predicting high risk of social network addiction of college students across machine learning models (top 10), figureFileSmall=9nQzZ/14GKDvXm/7w9b3Xw==, figureFileBig=EtEqTaZCxPddd2xbmFc1PA==, tableContent=null), ArticleFig(id=1325533121785119120, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, label=图1, caption=各机器学习模型对大学生社交网络成瘾高风险预测的特征重要性梯度(前10)

注:ASRS为成人注意缺陷/多动障碍自评量表。

, figureFileSmall=9nQzZ/14GKDvXm/7w9b3Xw==, figureFileBig=EtEqTaZCxPddd2xbmFc1PA==, tableContent=null), ArticleFig(id=1325533127644561809, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=EN, label=Tab.1, caption=

Comparison of scale scores among different social network addiction groups of college students(x ±s)

, figureFileSmall=null, figureFileBig=null, tableContent=
SNA风险组人数SNAS-CASRS物质使用烟草使用酒精使用人格解离症状强迫症状记忆问题睡眠问题
低11 46249.75±15.2822.87±11.330.14±0.450.30±0.730.26±0.580.96±1.350.46±0.681.09±1.350.60±0.760.70±0.80
高1 07980.33±6.3630.21±10.810.21±0.540.41±0.840.38±0.691.72±1.670.80±0.851.91±1.660.98±0.901.08±0.93
t值-126.87-21.23-4.23-4.33-5.64-14.38-12.98-15.76-13.33-12.89
P值< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01
SNA风险组人数精神病性症状自杀意念躯体化焦虑躁狂愤怒抑郁学业压力学业满意度
低11 4621.05±1.680.30±0.611.21±1.322.24±2.011.55±1.350.78±0.751.67±1.421.43±0.953.71±0.88
高1 0791.75±2.070.52±0.761.89±1.513.41±2.232.10±1.441.17±0.852.47±1.581.86±0.993.37±0.91
t值-10.81-9.03-14.38-16.73-12.25-14.72-16.12-13.8111.58
P值< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01
), ArticleFig(id=1325533130748346771, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, language=CN, label=表1, caption=

不同社交网络成瘾组别大学生各量表得分比较(x ±s)

, figureFileSmall=null, figureFileBig=null, tableContent=
SNA风险组人数SNAS-CASRS物质使用烟草使用酒精使用人格解离症状强迫症状记忆问题睡眠问题
低11 46249.75±15.2822.87±11.330.14±0.450.30±0.730.26±0.580.96±1.350.46±0.681.09±1.350.60±0.760.70±0.80
高1 07980.33±6.3630.21±10.810.21±0.540.41±0.840.38±0.691.72±1.670.80±0.851.91±1.660.98±0.901.08±0.93
t值-126.87-21.23-4.23-4.33-5.64-14.38-12.98-15.76-13.33-12.89
P值< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01
SNA风险组人数精神病性症状自杀意念躯体化焦虑躁狂愤怒抑郁学业压力学业满意度
低11 4621.05±1.680.30±0.611.21±1.322.24±2.011.55±1.350.78±0.751.67±1.421.43±0.953.71±0.88
高1 0791.75±2.070.52±0.761.89±1.513.41±2.232.10±1.441.17±0.852.47±1.581.86±0.993.37±0.91
t值-10.81-9.03-14.38-16.73-12.25-14.72-16.12-13.8111.58
P值< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01< 0.01
)], attaches=null, journal=Journal(id=1256213067906957319, delFlag=0, nameCn=中国学校卫生, nameEn=Chinese Journal of School Health, nameHistory1=null, nameHistory2=null, issn=1000-9817, eissn=null, cn=34-1092/R, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=AekpsZEgWlLz35HByrmLfA==, journalPrice=null, startedYear=null, abbrevIsoEn=Chinese Journal of School Health, journalRemark=null, publicationField=null, createdTime=1777434134703, updatedTime=1788949071540, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Medical and Pharmaceutical Sciences, subjectName=null, subjectCodeEn=Medical and Pharmaceutical Sciences, subjectNameEn=null, picCn=AekpsZEgWlLz35HByrmLfA==, picEn=Kyo4DrdVdhYZoe6v0NlLgg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304510214938583098, language=CN, name=中国学校卫生, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949071869, updatedTime=1788949071869, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://xiws.cbpt.cnki.net/EditorC3N/index.aspx?t=1, submissionEditorUrl=https://xiws.cbpt.cnki.net/EditorC3N/index.aspx?t=3, submissionReviewUrl=https://xiws.cbpt.cnki.net/EditorC3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304510214993109051, language=EN, name=Chinese Journal of School Health, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788949071882, updatedTime=1788949071882, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://xiws.cbpt.cnki.net/EditorC3N/index.aspx?t=1, submissionEditorUrl=https://xiws.cbpt.cnki.net/EditorC3N/index.aspx?t=3, submissionReviewUrl=https://xiws.cbpt.cnki.net/EditorC3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1256213402557890569, websiteList=[Website(id=1256214443441140376, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1256213402557890569, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgxxws/CN, language=CN, createTime=1777434462652, createBy=18614031015, updateTime=1777434574881, updateBy=18614031015, name=中国学校卫生-中文, tplId=1146099689490845704, title=中国学校卫生, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1256215107684655897, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=articleTextType, value=kx, createTime=1777434621020, updateTime=1777434621020, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107663684374, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=banner, value=null, createTime=1777434621015, updateTime=1777434621015, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107709821724, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=grayFlag, value=0, createTime=1777434621026, updateTime=1777434621026, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107651101461, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=logo, value=https://castjournals.cast.org.cn/joweb/zgxxws/CN/file/pic?fileId=SD0zLW2e5Vm+XCN1zUmHPA==, createTime=1777434621012, updateTime=1777434621013, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107726598942, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=minRunFlag, value=0, createTime=1777434621030, updateTime=1777434621030, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107680461592, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgxxws/CN/file/pic, createTime=1777434621019, updateTime=1777434621019, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107714016029, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=silenceFlag, value=0, createTime=1777434621027, updateTime=1777434621027, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107672072983, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1777434621017, updateTime=1777434621017, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107693044506, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=themeColor, value=null, createTime=1777434621022, updateTime=1777434621022, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215107701433115, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443441140376, code=themeStyle, value=null, createTime=1777434621024, updateTime=1777434621024, creator=18614031015, updator=18614031015)]), Website(id=1256214443571163802, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1256213402557890569, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgxxws/EN, language=EN, createTime=1777434462683, createBy=18614031015, updateTime=1777434571098, updateBy=18614031015, name=中国学校卫生-英文, tplId=1146101810881728533, title=Chinese Journal of School Health, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1256215133538345763, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=articleTextType, value=kx, createTime=1777434627184, updateTime=1777434627184, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133513179936, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=banner, value=null, createTime=1777434627178, updateTime=1777434627178, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133588677414, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=grayFlag, value=0, createTime=1777434627196, updateTime=1777434627196, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133475431199, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=logo, value=https://castjournals.cast.org.cn/joweb/gywlxb/EN/file/pic?fileId=SD0zLW2e5Vm+XCN1zUmHPA==, createTime=1777434627169, updateTime=1777434627169, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133601260328, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=minRunFlag, value=0, createTime=1777434627199, updateTime=1777434627199, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133529957154, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gywlxb/EN/file/pic, createTime=1777434627182, updateTime=1777434627182, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133592871719, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=silenceFlag, value=0, createTime=1777434627197, updateTime=1777434627197, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133521568545, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1777434627180, updateTime=1777434627180, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133567705892, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=themeColor, value=null, createTime=1777434627191, updateTime=1777434627191, creator=18614031015, updator=18614031015), WebsiteProps(id=1256215133580288805, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1256214443571163802, code=themeStyle, value=null, createTime=1777434627194, updateTime=1777434627194, creator=18614031015, updator=18614031015)])], journalTitle=中国学校卫生, weixinUrl=null, journalUrl=http://www.cjsh.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Journal of School Health, journalPhotoCn=AekpsZEgWlLz35HByrmLfA==, journalPhotoEn=Kyo4DrdVdhYZoe6v0NlLgg==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgxxws/CN/10.16835/j.cnki.1000-9817.2025323, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgxxws/EN/10.16835/j.cnki.1000-9817.2025323, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgxxws/CN/PDF/10.16835/j.cnki.1000-9817.2025323, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgxxws/EN/PDF/10.16835/j.cnki.1000-9817.2025323, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1764000000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于多算法机器学习的大学生社交网络成瘾风险预测模型
收藏切换
PDF下载
罗琳
中国学校卫生 | 心理卫生 2025,46(11): 1584-1589
收起
收藏切换
中国学校卫生 |心理卫生 2025 , 46 (11) : 1584 -1589
基于多算法机器学习的大学生社交网络成瘾风险预测模型
全屏
[Author(id=1325533104273899904, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325533105024680322, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, authorId=1325533104273899904, language=EN, stringName=Lin LUO, firstName=Lin, middleName=null, lastName=LUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Physical Education, Guizhou Normal University/Key Laboratory of Brain Function and Brain Disease Prevention and Treatment of Guizhou Province, Guiyang 550025, Guizhou Province, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325533107239272835, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, authorId=1325533104273899904, language=CN, stringName=罗琳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025, bio={"content":"

罗琳(1979-),女,贵州贵阳人,博士,教授,主要研究方向为体育健康传播与健康教育

"}, bioImg=null, bioContent=

罗琳(1979-),女,贵州贵阳人,博士,教授,主要研究方向为体育健康传播与健康教育

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325533103443427708, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, xref=null, ext=[AuthorCompanyExt(id=1325533103456010621, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, companyId=1325533103443427708, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Physical Education, Guizhou Normal University/Key Laboratory of Brain Function and Brain Disease Prevention and Treatment of Guizhou Province, Guiyang 550025, Guizhou Province, China), AuthorCompanyExt(id=1325533103472787838, tenantId=1146029695717560320, journalId=1256213402557890569, articleId=1325533078244049270, companyId=1325533103443427708, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025)])])]
罗琳
作者信息
  • 贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025
作者简介:

罗琳(1979-),女,贵州贵阳人,博士,教授,主要研究方向为体育健康传播与健康教育

Prediction model for the risk of social network addiction among college students based on multi-algorithm machine learning approaches
Lin LUO
Affiliations
  • School of Physical Education, Guizhou Normal University/Key Laboratory of Brain Function and Brain Disease Prevention and Treatment of Guizhou Province, Guiyang 550025, Guizhou Province, China
出版时间: 2025-11-25 doi: 10.16835/j.cnki.1000-9817.2025323
文章导航
收藏切换
目的

构建多种机器学习模型识别大学生社交网络成瘾(SNA)高风险个体,筛选关键预测因子,为精准筛查与干预提供循证依据。

方法

于2024年9—10月,采用多阶段整群抽样抽取贵州省某大学城5所高校12 541名本科生为对象,采用中文版社交网络成瘾量表(SNAS-C)、成人注意缺陷/多动障碍自评量表(ASRS)、《精神疾病诊断与统计手册第五版》自评水平1横切症状测量-成人中文版(DSM-5 CCSM)、学业压力与学业满意度问卷,以及24 h活动指南进行问卷调查。采用多层感知机神经网络(MLP)、XGBoost、K近邻(KNN)和梯度提升决策树(GBDT)4种机器学习模型,按8∶2划分训练集与测试集,利用准确率、召回率、F1值和ROC曲线下面积(AUC)评估模型性能,并进一步开展特征重要性分析。

结果

SNA高风险检出率为8.60%,女生(10.10%)高于男生(6.74%),差异有统计学意义(χ2=44.42,P < 0.01)。相比SNA低风险组,高风险组ASRS得分更高,抑郁、焦虑等更严重,学业压力更大、满意度更低(t值分别为-21.23,-16.12,-16.73,-13.81,11.58,P值均 < 0.01)。在24 h活动行为中(身体活动、睡眠、久坐/屏幕时间),SNA高风险组达标率(11.77%,5.65%,57.92%)相比低风险组(15.57%,13.16%,75.32%)偏低(χ2值分别为11.04,50.72,154.40,P值均 < 0.01)。4种模型均具良好区分度,其中XGBoost表现最佳(准确率88.18%,F1=0.881),KNN的AUC最高(0.90)。特征重要性分析显示ASRS为SNA最关键预测因子,其次为学业压力、抑郁、年龄和学业满意度。

结论

机器学习模型可有效识别大学生SNA高风险个体;注意缺陷症状、内化问题和学业压力是主要风险因素,24 h活动行为(尤其睡眠与屏幕时间)为关键干预靶点。

信息交流  /  因特网  /  行为,成瘾  /  精神卫生  /  学生
Objective

To develop multiple machine learning models to identify college students at high risk of social network addiction (SNA) and to select key predictors, so as to provide evidences for tiered screening and interventions.

Methods

A multi-stage cluster sampling was conducted among 12 541 undergraduates at five universities in Guizhou Province from September to October 2024. The Chinese version of Social Networking Addiction Scale (SNAS-C) was used to classify high-risk individuals. Candidate variables included demographic characteristics, the total scores of Adult ADHD Self-report Scale (ASRS) and the Chinese version of Diagnostic and Statistical Manual of Mental Disorders, 5th Edition Self-rated level 1 Cross-cutting Symptom Measure (DSM-5 CCSM), academic stress and academic satisfaction and 24-hour Movement Guidelines. Four machine learning models including multilayer perceptron neural network (MLP), XGBoost, K-nearest neighbors (KNN), and gradient boosting decision trees (GBDT) were trained with an 8∶2 train-test split. Model performance was evaluated using accuracy, recall, F1 score, and the area under the ROC curve (AUC), followed by feature importance analysis.

Results

The detection rate of high-risk SNA was 8.60%, higher in girls (10.10%) than boys (6.74%), with a statistically significant difference (χ2=44.42, P < 0.01). Compared with the low-risk group for SNA, the high-risk group had higher ASRS scores, more severe of depression and anxiety, greater academic stress, and lower academic satisfaction (t=-21.23, -16.12, -16.73, -13.81, 11.58, all P < 0.01). Regarding 24-hour movement behaviors (physical activity, sleep, sedentary/screen time), the high-risk SNA group showed lower compliance rates (11.77%, 5.65%, 57.92%) than the low-risk group (15.57%, 13.16%, 75.32%) (χ2=11.04, 50.72, 154.40, all P < 0.01). All four models demonstrated good discrimination; XGBoost performed the best (accuracy 88.18%, F1=0.881), while KNN achieved the highest AUC (0.90). Feature importance analysis indicated ASRS as the most critical predictor of SNA, followed by academic stress, depression, age, and academic satisfaction.

Conclusions

Machine learning models can effectively identify college students at high risk for SNA. ADHD symptoms, internalizing problems, and academic stress are major risk factors, while 24-hour movement behaviors are key intervention targets, especially sleep and screen time.

Communication  /  Internet  /  Behavior, addictive  /  Mental health  /  Students
罗琳. 基于多算法机器学习的大学生社交网络成瘾风险预测模型. 中国学校卫生, 2025 , 46 (11) : 1584 -1589 . DOI: 10.16835/j.cnki.1000-9817.2025323
Lin LUO. Prediction model for the risk of social network addiction among college students based on multi-algorithm machine learning approaches[J]. Chinese Journal of School Health, 2025 , 46 (11) : 1584 -1589 . DOI: 10.16835/j.cnki.1000-9817.2025323
随着社交网站和互联网迅速普及,智能手机等数字工具已成为人们日常生活的“基础设施”[1-2]。数字环境正在重塑大学生的学习与人际互动。一方面,在线社交网络有助于促进社会接纳和文化适应[3]; 另一方面,在线互动亦可能促进自主学习和写作[4]。社交媒体参与在一定程度上改变了身份发展进程,既带来机遇,也伴随风险[5]。
网络成瘾的流行率在不同地区和研究间差异显著[5-6],这种差异与量表、阈值、抽样和人群结构等因素相关[6-7]。调查显示,约95%的学生每日上网超过2 h,主要用于学业和职业发展,但不少学生报告难以自控,课程表现受影响[7]。随着使用时长、互动频率与算法推送叠加,部分学生出现抑制失败、戒断不适、耐受增强及学业和睡眠受损等典型社交网络成瘾(social network addiction,SNA)特征[8-12],并伴随情绪症状、满意度下降、压力升高和社会功能受损[13]。在人群差异方面,女性更常使用微博、小红书等平台[14-15]; 男性更易出现问题性使用[16]; 且随年龄增长,成瘾风险递减[17]。近年来,机器学习在行为与健康领域的应用不断拓展,显示良好的判别力与可迁移性[18-19]。鉴于不同算法在建模、特征评估、可解释性与效率上的差异,本研究采用多算法并行策略,通过整合神经网络、集成树与基于距离的模型,识别最优预测工具,为构建科学可靠的大学生SNA预测模型奠定方法学基础。
采用多阶段整群抽样,抽取贵州省某大学城5所高校在读本科生为对象,于2024年9—10月开展线上与线下相结合的问卷调查。共获得有效应答问卷12 766份,年龄18~29岁,受访者户籍分布于全国12个省级行政区(包括贵州、广西、重庆、四川、北京、江西、山东、河南、黑龙江、河北、湖南、云南)。剔除225名自报“既往经专业机构确诊为精神障碍”的个体,最终纳入12 541份问卷,有效率为98.2%。其中男生5 579名,女生6 962名; 大一学生7 151名,大二4 978名,大三412名。研究方案获贵州师范大学科研伦理委员会批准(批号:20230300005),所有参与者均签署了知情同意书。
采用自填式问卷收集性别、年龄与年级等基本信息。
量表基于“成瘾六要素模型”[2]编制,共21个条目,采用Likert 5点计分(1~5分),总分21~105分[20]。本研究中该量表的Cronbach α系数为0.958。参考Luo等[21]研究,将≥72分界定为高风险, < 72分为低风险。
由世界卫生组织开发,共18个条目,采用Likert 5点计分(0=“从未”至4=“非常频繁”),总分0~72分,回溯期6个月[22-23]。中文版已证实信效度良好[24],本研究中该量表的Cronbach α系数为0.954。
该量表包含23个条目,覆盖物质使用、烟草使用、酒精使用、人格、解离症状、强迫症状、记忆问题、睡眠问题、精神病性症状、自杀意念、躯体症状、焦虑、躁狂、愤怒以及抑郁15个精神病理维度。采用Likert 5点计分(0=“无,根本没有”至4=“严重,几乎每天”),回溯期2周。既往研究表明其信效度优良[24]。本研究中该量表的Cronbach α系数为0.897。
采用自编单题量表,学业压力通过“学习任务带来的压力程度”评估,采用5分评分(1=“无压力”~5=“极大压力”); 学业满意度通过“学习体验满意度”评估,采用5分评分(1=“非常不满意”~5=“非常满意”)。该量表参考Cohen与Diener框架设计并经预测试优化[27-28],前期研究已验证其关联效度[21, 23]。两项得分在建模前均进行了标准化处理。
依据加拿大24 h活动指南(24-hour Movement Guidelines, 24-HMG)[29],测量身体活动、久坐/屏幕时间与睡眠3个方面行为[30-32]:(1)每周中高强度活动≥150 min; (2)每天久坐≤8 h且娱乐性屏幕时间≤180 min; (3)夜间睡眠7~9 h,3项均二元编码(1=达标,0=未达标)。问卷区分娱乐性与学业/工作屏幕使用,并在数据清理阶段实施逻辑校验与截尾处理。
统一培训调查员并开展小样本预测试,校准问卷条目与合理作答时长; 线上设置必答、逻辑跳转与时长阈值,线下现场核查缺漏; 通过一致性与逻辑校验、直线/异常作答与极端时长识别剔除可疑问卷,并对连续变量实施合理截尾; 评估信度与效度,并在必要时进行敏感性分析以确保结果稳健。
数据录入与描述性统计使用SPSS 27.0软件完成。计数资料以频数和率表示,计量资料以均值和标准差描述。Shapiro-Wilk检验显示大部分变量偏离正态分布,因此组间比较采用χ2检验和Welch t检验。共同方法偏差通过Harman单因子检验评估。双侧检验水准α=0.05。
为预测大学生社交网络成瘾,选取24个候选自变量,包括人口学特征(性别、年级、年龄)、ASRS总分、DSM-5 CCSM 15个维度得分、学业压力、学业满意度及24 h活动行为(3项指标)。样本按8∶2分层随机划分为训练集(n=10 033)和测试集(n=2 508)。为处理类别不平衡,在训练集中应用SMOTE采样。所有模型均在训练集完成训练与参数优化,并采用10×10倍交叉验证以增强泛化能力并控制过拟合。采用多层感知机(multilayer perceptron, MLP)、极端梯度提升算法(extreme gradient boosting, XGBoost)、K近邻算法(K-nearest neighbors, KNN)和梯度提升决策树(gradient boosting decision tree, GBDT)4种模型进行分类预测。模型性能通过准确率(accuracy)、召回率(recall)、F1分数(F1-score)以及ROC曲线下面积(area under the curve, AUC)进行评估。
采用Harman单因子法对所有自陈量表条目进行未旋转主成分分析。结果显示,特征根大于1的公因子不止一个,且最大公因子解释率 < 40%,表明不存在严重的共同方法偏差,后续分析可信。
男生SNA高风险检出率为6.74%(376名),女生为10.10%(703名); 大一、大二、大三学生检出率分别为7.94%(568名),9.46%(471名),9.71%(40名),性别和年级间差异均有统计学意义(χ2值分别为44.42,9.27,P值均<0.01)。与低风险组相比,高风险组在ASRS总分及DSM-5 CCSM多个维度(抑郁、躁狂、焦虑、躯体化、自杀意念、精神病性症状、睡眠、记忆、强迫、解离、人格功能及物质使用等)评分均更高; 高风险组学业压力较大、学业满意度更低(P值均 < 0.01)。见表1。高、低风险组年龄分别为(19.49±1.41,19.66±1.66)岁,差异均有统计学意义(t=3.67,P < 0.01)。在24 h活动行为方面,相比低风险组达标率(15.57%,1 785名; 13.16%,1 508名; 75.32%,8 633名),高风险组大学生的身体活动(11.77%,127名)、睡眠(5.65%,61名)和久坐/屏幕时间(57.92%,625名)均较低,差异均有统计学意义(χ2值分别为11.04,50.72,154.40,P值均<0.01)。
整体来看,4类算法模型在精确度、召回率、F1和AUC值上均表现出较高水平。其中XGBoost在精确度与召回率上表现最佳(分别为88.18%和91.60%),F1为0.88,AUC为0.83;GBDT在F1值方面优势最为突出(0.89),但其精确度为87.46%,召回率为90.99%,AUC为0.82;KNN则在AUC指标上达到最高(0.90),其精确度为85.51%,召回率为91.04%,F1为0.88;MLP的精确度为86.35%,召回率为90.99%,F1为0.88,AUC为0.83,显示出在区分高低风险人群方面的较强判别力。
以24个候选变量为自变量,以SNA高风险为因变量,开展特征重要性分析。重要性度量综合采用模型内置指标与置换重要性,并经标准化后排序。结果显示,各类模型均能稳定识别出一组贡献度较高的特征,其中ASRS总分在所有树模型中均排首位。见图1。
具体排序方面,XGBoost的前5位特征依次为ASRS(0.076)、久坐/屏幕时间(0.062)、强迫症状(0.057)、学业压力(0.052)、性别(0.047);GBDT的前5位特征为ASRS(0.188)、学业压力(0.058)、强迫症状(0.056)、抑郁(0.052)、躯体化(0.051)。
综合4类模型结果,ASRS总分始终是最关键的预测因子; 学业压力、抑郁、焦虑、年龄与学业满意度多次进入前列,显示出稳定的重要性; 强迫症与躯体化在多模型中贡献度处于中等偏高水平,而久坐/屏幕时间与性别在部分模型中具有额外解释力。结合Shapley加性解释(Shapley addictive explanations, SHAP)分析可见,在个体层面,ASRS、抑郁/焦虑及睡眠问题得分越高,SNA高风险预测概率越大; 相反,良好的睡眠与达标的久坐/屏幕时间与SNA较低风险相关。
本研究在12 541名大学生中检出8.6%的SNA高风险个体,低于部分研究的15%~20%[5-6],但接近中国高校“广义互联网成瘾”水平(约7%~11%)[33]。差异可能与量表、阈值及样本背景有关[34]。女生检出率高于男生,提示其在情绪调节与社会联结需求上存在更强的依赖[35]。高风险组表现为ASRS、抑郁、焦虑等得分更高,学业压力更大、满意度更低,同时身体活动与睡眠达标率下降、久坐/屏幕时间过长,印证了SNA的多维风险特征。
4类机器学习模型均具良好效能。XGBoost在准确率与召回率上表现最佳,GBDT的F1值最高,KNN在AUC上优势明显,而MLP各项指标均衡。总体格局符合算法特性:集成树模型适合处理高维非线性交互,KNN在阈值判别上敏感,而MLP易受网络结构与正则化影响[36]。结果与既有研究一致,即在行为—心理—学业多维特征结合的情境下,集成模型往往优于传统回归模型[37-38]。
特征重要性分析显示出跨模型一致的“核心特征簇”。ASRS总分在所有树模型中始终居首,表明注意控制脆弱性是SNA的关键风险表征,与执行功能障碍导致的自控力下降一致[39]。学业压力和抑郁/焦虑稳定进入前列,反映“内化问题—慢性应激”在SNA中的作用,与既有研究结论一致[8-12]。此外,年龄与学业满意度因素显示发展阶段和学习体验的重要性[40]; 强迫与躯体化中等贡献,可能与刷屏行为和情绪—躯体化应对有关[41]。XGBoost还凸显了久坐/屏幕时间与性别因素的重要性,提示使用强度和情境差异需关注。
据此,本研究提出“易感—应激—行为”框架:注意/执行功能脆弱性在学业压力与内化症状的叠加下,通过睡眠受损与屏幕暴露延长进一步增加风险。既有研究已表明执行功能缺陷与情绪障碍会通过行为途径放大成瘾倾向[42]。结合SHAP解释可见,ASRS、抑郁/焦虑和睡眠问题得分越高,预测概率越大; 而良好睡眠与适度屏幕时间与低风险相关,与近期研究发现一致[43]。
在实践层面,结果提示筛查应优先关注ASRS、抑郁/焦虑、学业压力及24 h活动行为,并结合可解释模型开展分层评估。干预方面,可聚焦注意训练与情绪调节,已有研究证明其可减轻成瘾症状并改善心理健康[44]。同时,应加强学业负荷与时间管理,优化学生的学习与社交平衡[45]。在情境层面,推广数字卫生教育与睡眠友好作息,结合“增加活动—减少久坐—改善睡眠”的综合路径,与社会生态干预框架相契合[7]。
本研究局限性包括横断面设计、自陈数据偏倚、地域样本外推不足,以及缺乏外部验证和公平性评估。未来研究应开展多中心纵向研究,引入可穿戴设备与平台日志等多模态数据,并加强模型的验证、校准与公平性分析,以推动可解释人工智能在分层筛查和个性化干预中的应用。
  • 国家自然科学基金项目(72364006);贵州省科技计划项目(黔科合基础-ZK[2023]一般251)
参考文献 引证文献
排序方式:
1
BUCTOT D B, KIM N, KIM J J. Factors associated with smartphone addiction prevalence and its predictive capacity for health-related quality of life among Filipino adolescents[J]. Child Youth Serv Rev, 2020, 110: 104758.
2
KUSS D, GRIFFITHS M. Social networking sites and addiction: ten lessons learned[J]. Int J Environ Res Public Health, 2017, 14(3): 311.
3
YU A Y, TIAN S W, VOGEL D, et al. Can learning be virtually boosted? An investigation of online social networking impacts[J]. Comput Educ, 2010, 55(4): 1494-1503.
4
YIN H, SHI L. Which type of interpersonal interaction better facilitates college student learning and development in China: face-to-face or online?[J]. ECNU Rev Educ, 2021, 5(1): 9-36.
5
BI S, YUAN J, LUO L. The Social Networking Addiction Scale: tran-slation and validation study among Chinese college students[J]. Int J Ment Health Promot, 2024, 26: 51-60.
6
MACHIMBARRENA J M, GONZÁLEZ-CABRERA J, ORTEGA-BA-RÓN J, et al. Profiles of problematic Internet use and its impact on adolescents' health-related quality of life[J]. Int J Environ Res Public Health, 2019, 16(20). DOI: 10.3390/ijerph16203877.
7
ZHOU R, XIA D, YIN Y, et al. Analyzing the impact of the Internet on higher education[J]. Int J Secur Appl, 2016, 10(6): 341-350.
8
HOU Y, XIONG D, JIANG T, et al. Social media addiction: its impact, mediation, and intervention[J]. Cyberpsychology, 2019, 13(1): 1-17.
9
SUN Y, ZHANG Y. A review of theories and models applied in studies of social media addiction and implications for future research[J]. Addict Behav, 2021, 114: 106699.
10
GRIFFITHS M D, KUSS D. Adolescent social media addiction (revisited)[J]. Educ Health, 2017, 35(3): 49-52.
11
CHENG C, LAU Y C, CHAN L, et al. Prevalence of social media addiction across 32 nations: Meta-analysis with subgroup analysis of classification schemes and cultural values[J]. Addict Behav, 2021, 117: 106845.
12
DUMITRESCU M, DUMITRESCU N, TURLIUC S. The social media addiction: what have we learned so far?-a review[J]. BRAIN Broad Res Artif Intell Neurosci, 2023, 14(1): 117-137.
13
CHEN B, LIU F, DING S, et al. Gender differences in factors associated with smartphone addiction: a cross-sectional study among medical college students[J]. BMC Psychiatry, 2017, 17(1): 341.
14
CIMADEVILLA R, JENARO C. Impact on psychological health of Internet and mobile phone abuse in a Spanish sample of secondary students[J]. Revist Argent De Clínic Psicol, 2019, 28(3): 339-347.
15
BISCHOF-KASTNER C, KUNTSCHE E, WOLSTEIN J. Identifying problematic Internet users: development and validation of the Internet Motive Questionnaire for Adolescents (IMQ-A)[J]. J Med Internet Res, 2014, 16(10): e230.
16
BRANLEY D B, COVEY J. Risky behavior via social media: the role of reasoned and social reactive pathways[J]. Comput Hum Behav, 2018, 78: 183-191.
17
LACONI S, KALISZEWSKA-CZEREMSKA K, GNISCI A, et al. Cross-cultural study of problematic Internet use in nine European countries[J]. Comput Hum Behav, 2018, 84: 430-440.
18
JORDAN M I, MITCHELL T M. Machine learning: trends, perspectives, and prospects[J]. Science, 2015, 349(6245): 255-260.
19
LUO L, YUAN J, WU C, et al. Predictors of depression among Chinese college students: a machine learning approach[J]. BMC Public Health, 2025, 25(1): 470.
20
SHAHNAWAZ M G, REHMAN U. Social Networking Addiction Scale[J]. Cogent Psychol, 2020, 7: 1832032.
21
LUO L, YUAN J, WANG Y, et al. Possible classifications of social network addiction: a latent profile analysis of Chinese college students[J]. Int J Ment Health Promot, 2025, 27(6): 863-876.
22
KESSLER R C, ADLER L, AMES M, et al. The World Health Organization Adult ADHD Self-report Scale (ASRS): a short screening scale for use in the general population[J]. Psychol Med, 2005, 35(2): 245-256.
23
LUO L, YUAN J, XU C, et al. Mental health issues and 24-hour movement guidelines-based intervention strategies for university students with high-risk social network addiction: cross-sectional study using a machine learning approach[J]. J Med Internet Res, 2025, 27: e72260.
24
陈琳, 许诗玮, 罗学荣. 长沙市大学生注意缺陷多动障碍及影响因素[J]. 中国学校卫生, 2020, 41(12): 1856-1858, 1862.
CHEN L, XU S W, LUO X R. Prevalence and risk factors of attention deficit hyperactivity disorder among college students in Changsha[J]. Chin J Sch Health, 2020, 41(12): 1856-1858, 1862. (in Chinese)
25
BRAVO A J, PEARSON M R, STEVENS L E. The DSM-5 self-rated level 1 cross-cutting symptom measure: psychometric properties and associations with alcohol use and related outcomes[J]. J Substance Abuse Treatment, 2018, 94: 1-7.
26
MA Y, LI W, WANG X. Psychometric properties of the DSM-5 self-rated level 1 cross-cutting symptom measure in Chinese adults[J]. J Affect Disord, 2021, 282: 1236-1243.
27
COHEN S, KAMARCK T, MERMELSTEIN R. A global measure of perceived stress[J]. J Health Soc Behav, 1983, 24(4): 385-396.
28
DIENER E, EMMONS R A, LARSEN R J, et al. The satisfaction with life scale[J]. J Pers Assess, 1985, 49(1): 71-75.
29
TREMBLAY M S, CARSON V, CHAPUT J P. Introduction to the Canadian 24-hour movement guidelines for children and youth: an integration of physical activity, sedentary behaviour, and sleep[J]. Appl Physiol Nutr Metab, 2016, 41(6 Suppl 3): Ⅲ-Ⅳ.
30
LUO L. 24-h movement behaviors and visual impairment among Chinese adolescents with and without obesity[J]. Compl Ther Clin Pract, 2024, 54: 101823.
31
LUO L, CAO Y, HU Y, et al. The associations between meeting 24-hour movement guidelines (24-HMG) and self-rated physical and mental health in older adults: cross sectional evidence from China[J]. Int J Environ Res Public Health, 2022, 19(20): 3407.
32
LUO L, ZENG X, CAO Y, et al. The associations between meeting 24-hour movement guidelines (24-HMG) and mental health in adolescents: cross sectional evidence from China[J]. Int J Environ Res Public Health, 2023, 20(4): 3167.
33
DUC T Q, CHI V T Q, HUYEN N T H, et al. Growing propensity of Internet addiction among Asian college students: Meta-analysis of pooled prevalence from 39 studies with over 50 000 participants[J]. Public Health, 2024, 227: 250-258.
34
LEÓN MÉNDEZ M, PADRÓN I, FUMERO A, et al. Effects of Internet and smartphone addiction on cognitive control in adolescents and young adults: a systematic review of fMRI studies[J]. Neurosci Biobehav Rev, 2024, 159: 105572.
35
KENDLER K S, GARDNER C O. Sex differences in the pathways to major depression: a study of opposite-sex twin pairs[J]. Am J Psychiatry, 2014, 171(4): 426-435.
36
ZHOU W, YAN Z, ZHANG L. A comparative study of 11 non-linear regression models highlighting autoencoder, DBN, and SVR, enhanced by SHAP importance analysis in soybean branching prediction[J]. Sci Rep, 2024, 14(1): 5905.
37
SUN Y, LI Z, LI X, et al. Classifier selection and ensemble model for multi-class imbalance learning in education grants prediction[J]. Appl Artif Intell, 2021, 35(4): 290-303.
38
GURJAR S, PATIL C, SURYAWANSHI R, et al. Mental health prediction using machine learning[J]. Internl Res J Engineer Technol, 2022, 9(5): 2395-0056.
39
SARIYSKA R, REUTER M, LACHMANN B, et al. Attention deficit/hyperactivity disorder is a better predictor for problematic Internet use than depressione: evidence from Germany[J]. J Addiction Research Therapy, 2015, 6(209): 1-6.
40
TANG J, YU Y, DU Y, et al. Prevalence of Internet addiction and its association with stressful life events and psychological symptoms among adolescent Internet users[J]. Addict Behav, 2014, 39(3): 744-747.
41
BRAND M, YOUNG K S, LAIER C. Prefrontal control and Internet addiction: a theoretical model and review of neuropsychological and neuroimaging findings[J]. Front Hum Neurosci, 2014, 8: 375.
42
DONG G, POTENZA M N. A cognitive-behavioral model of Internet gaming disorder: theoretical underpinnings and clinical implications[J]. J Psychiatr Res, 2014, 58: 7-11.
43
ALIMORADI Z, LIN C Y, BROSTRÖM A, et al. Internet addiction and sleep problems: a systematic review and Meta-analysis[J]. Sleep Med Rev, 2019, 47: 51-61.
44
WINKLER A, DÖRSING B, RIEF W, et al. Treatment of Internet addiction: a Meta-analysis[J]. Clin Psychol Rev, 2013, 33(2): 317-329.
45
SHEN X, WANG C, CHEN C, et al. Stress and Internet addiction: mediated by anxiety and moderated by self-control[J]. Psychol Res Behav Manag, 2023, 16: 1975-1986.
2025年第46卷第11期
PDF下载
6
3
引用本文
BibTeX
文章信息
doi: 10.16835/j.cnki.1000-9817.2025323
  • 接收时间:2025-08-01
  • 首发时间:2026-11-06
  • 出版时间:2025-11-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-08-01
  • 修回日期:2025-09-07
基金
国家自然科学基金项目(72364006);贵州省科技计划项目(黔科合基础-ZK[2023]一般251)
作者信息
    贵州师范大学体育学院/贵州省脑功能和脑疾病防治重点实验室, 贵阳 550025
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgxxws/CN/10.16835/j.cnki.1000-9817.2025323
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏