Construction of Question Answering System for Suicide Tendency Detection Based on Knowledge Graph

doi:10.3778/j.issn.1002-8331.2103-0038

Abstract

Abstract:

Due to the people lack of psychological knowledge, the prevalence rate of mental illness is rising rapidly. In order to solve the problem, a small psychological counseling knowledge graph and Question Answering system（QA） is constructed. The system can help consultants to acquire psychological knowledge in time, also can identify the consultants who have suicidal tendency to prevent the occurrence of danger. Firstly, collect some psychological information data to build the dictionary, and generate entities and relationship to build the knowledge graph. Then, use the HanLP segmentation tool to generate keywords, and classify problems by CHI feature selection to improve the efficiency of QA system. By compared with other models, optimize BiLSTM model to construct the suicidal text classifier for detecting dangerous users’ speech. Finally, by computing the similarity score of template match, generate the answer. By testing the accuracy of the system, it is proved that the system can effectively answer the questions related to psychological counseling.

Key words: knowledge graph, question answering system, text classification, suicidality detection

摘要：

针对当今社会人们因缺乏心理知识而导致心理疾病患病率急剧上升的问题，构建了一个小型的心理咨询知识图谱与问答系统（Question Answering system，QA）。该系统可以帮助咨询者及时获取心理知识，也可以识别出有自杀倾向的咨询者，防止危险发生。搜集了一些心理信息数据，通过构建字典并生成实体与关系构建了知识图谱；使用了HanLP（Han Language Processing）分词工具来生成关键词，通过CHI（Chi-square）特征选择来进行问题分类，提高问答效率；通过与其他模型对比，优选BiLSTM（Bi-directional Long Short-Term Memory）模型构建了自杀倾向文本分类器来检测危险的用户发言；通过计算相似度得分来进行问题模板匹配并生成答案。最后进行系统正确率测试，证明了该系统可以有效回答心理咨询相关的问题。

关键词: 知识图谱, 问答系统, 文本分类, 自杀倾向检测

WU Shuzhao, LI Gongquan, BU Mingwei. Construction of Question Answering System for Suicide Tendency Detection Based on Knowledge Graph[J]. Computer Engineering and Applications, 2021, 57(22): 304-312.

武书钊，李功权，卜明伟. 基于知识图谱的自杀倾向检测问答系统构建[J]. 计算机工程与应用, 2021, 57(22): 304-312.

References

[1] YAMAGUCHI S，MINO Y，UDDIN S.Strategies and future attempts to reduce stigmatization and increase awareness of mental health problems among young people：a narrative review of educational interventions[J].Psychiatry and Clinical Neurosciences，2011，65（5）：405-415.
[2] MAR R A，OATLEY K.The function of fiction is the abstraction and simulation of social experience[J].Perspectives on Psychological Science，2010，3（3）：173-192.
[3] BAUMAN S，TOOMEY R B，WALKER J L.Associations among bullying，cyberbullying，and suicide in high school students[J].Journal of Adolescence，2013，36（2）：341-350.
[4] 李贞.心理咨询师的社会支持现状研究[D].南昌：江西中医药大学，2019.
LI Z.Research on the present situation of social support for psychological counselors[D].Nanchang：Jiangxi University of Traditional Chinese Medicine，2019.
[5] VANG K J.Ethics of Google’s knowledge graph：some considerations[J].Journal of Information Communication & Ethics in Society，2013，11（4）：245-260.
[6] PAULHEIM H，CIMIANO P.Knowledge graph refinement：a survey of approaches and evaluation methods[J].Semantic Web，2017，8（3）：489-508.
[7] MULANG I O，SINGH K，ORLANDI F.Matching natural language relations to knowledge graph properties for question answering[C]//Proceedings of the 13th International Conference on Semantic Systems，2017：89-96.
[8] BIZER C，LEHMANN J，KOBILAROV G，et al.DBpedia—a crystallization point for the web of data[J].Web Semantics Science Services & Agents on the World Wide Web，2009，7（3）：154-165.
[9] BOLLACKER K，EVANS C，PARITOSH P，et al.Freebase：a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data，2008：1247-1250.
[10] SUCHANEK F M，KASNECI G，WEIKUM G.YAGO：a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web，2007：697-706.
[11] 张德亮.面向金融领域的知识图谱构建及补全研究[D].青岛：青岛大学，2020.
ZHANG D L.Research on the construction and completion of knowledge graph oriented to financial field[D].Qingdao：Qingdao University，2020.
[12] 俞思伟，范昊，王菲，等.基于知识图谱的智能医疗研究[J].医疗卫生装备，2017，38（3）：109-111.
YU S W，FAN H，WANG F，et al.Research on intelligent medicine based on knowledge graph[J].Chinese Medical Equipment Journal，2017，38（3）：109-111.
[13] 谭刚，陈聿，彭云竹.融合领域特征知识图谱的电网客服问答系统[J].计算机工程与应用，2020，56（3）：232-239.
TAN G，CHEN Y，PENG Y Z.Hybrid domain feature knowledge graph smart question answering system[J].Computer Engineering and Applications，2020，56（3）：232-239.
[14] 陈金菊，王义真，欧石燕.基于道路法规知识图谱的多轮自动问答研究[J].现代情报，2020，40（8）：98-110.
CHEN J J，WANG Y Z，OU S Y.Research on multi-round automatic question answering based on knowledge graph of road regulations[J].Journal of Modern Information，2020，40（8）：98-110.
[15] 杜泽宇，杨燕，贺樑.基于中文知识图谱的电商领域问答系统[J].计算机应用与软件，2017，34（5）：153-159.
DU Z Y，YANG Y，HE L.Question answering system of electric business field based on Chinese knowledge graph[J].Computer Application and Software，2017，34（5）：153-159.
[16] 陈璟浩，曾桢，李纲.基于知识图谱的“一带一路”投资问答系统构建[J].图书情报工作，2020，64（12）：95-105.
CHEN J H，ZENG Z，LI G.A question answering system for the “belt and road” investment based on knowledge graph[J].Library and Information Service，2020，64（12）：95-105.
[17] 李超.基于深度学习的短文本分类及信息抽取研究[D].郑州：郑州大学，2017.
LI C.Short text classification and information extraction research based on deep learning[D].Zhengzhou：Zhengzhou Univercity，2017.
[18] ADACHI Y，ONIMURA N，YAMASHITA T，et al.Standard measure and SVM measure for feature selection and their performance effect for text classification[C]//Proceedings of the 18th International Conference on Information Integration and Web-Based Applications and Services，2016：262-266.
[19] RAJVANSHI N，CHOWDHARY K R.Comparison of SVM and na?ve Bayes text classification algorithms using WEKA[J].International Journal of Engineering & Technical Research，2017，6（9）：141-143.
[20] 刘思聪，卢甘霖，崔子良，等.基于XGBoost的中文网络评论分类方法研究[J].数码世界，2020（12）：226-227.
LIU S C，LU G L，CUI Z L，et al.Research on classification method of Chinese network comments based on XGBoost[J].Digital World，2020（12）：226-227.
[21] NOWAK J，TASPINAR A，SCHERER R.LSTM recurrent neural networks for short text and sentiment classification[C]//International Conference on Artificial Intelligence and Soft Computing，2017.
[22] 董彦如，刘培玉，刘文锋，等.基于双向长短期记忆网络和标签嵌入的文本分类模型[J].山东大学学报（理学版），2020，55（11）：78-86.
GONG Y R，LIU P Y，LIU W F，et al.A text classification model based on BiLSTM and label embedding[J].Journal of Shandong University（Natural Science），2020，55（11）：78-86.
[23] Chatopera Inc.Emotional first aid dataset[DB/OL].（2020-04-22）[2021-02-12].https：//github.com/chatopera/efaqa-corpus-zh.
[24] 胡力.面向心理咨询的语义本体库的构建[D].武汉：武汉科技大学，2014.
HU L.Construction of semantic ontology library for psychological-oriented consultation[D].Wuhan：Wuhan University of Science and Technology，2014.
[25] ZHU F，YE F，FU Y C，et al.Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network[J].Scientific Reports，2019，9：6734.
[26] 曹为政，葛蒙蒙.多模式匹配算法研究和优化[J].智能计算机与应用，2018，8（2）：129-133.
CAO W Z，GE M M.Multi-pattern matching algorithm research and optimization[J].Intelligent Computer and App-
lications，2018，8（2）：129-133.
[27] 曹东伟，李邵梅，陈鸿昶.基于GCN的虚假评论检测方法[J/OL].计算机工程与应用（2021-01-27）[2021-03-30].http：//kns.cnki.net/kcms/detail/11.2127.TP.20210127.1109.010.html.
CAO D W，LI S M，CHEN H C.Fake reviews detection method based on GCN[J/OL].Computer Engineering and Applications（2021-01-27）[2021-03-30].http：//kns.cnki.net/kcms/detail/11.2127.TP.20210127.1109.010.html.
[28] 王远超，安俊秀，程芃森，等.基于最优路径策略方法快速计算字符串编辑距离[J].成都信息工程学院学报，2014，29（6）：616-624.
WANG Y C，AN J X，CHENG P S，et al.Fast computing string edit distance based on the strategy of optimal path[J].Journal of Chengdu University of Information Technology，2014，29（6）：616-624.
[29] 高森.农业问答系统中问题分类和相似度计算的研究[D].合肥：中国科学技术大学，2019.
GAO S.Research on question classification and similarity calculation in agricultural question answering[D].Hefei：University of Science and Technology of China，2019.