Detecting Depression in Social Media using Fine-Grained Emotions

Nowadays social media platforms are the most popular way for people to share information, from work issues to personal matters. For example, people with health disorders tend to share their concerns for advice, support or simply to relieve suffering. This provides a great opportunity to proactively detect these users and refer them as soon as possible to professional help. We propose a new representation called Bag of Sub-Emotions (BoSE), which represents social media documents by a set of fine-grained emotions automatically generated using a lexical resource of emotions and subword embeddings. The proposed representation is evaluated in the task of depression detection. The results are encouraging; the usage of fine-grained emotions improved the results from a representation based on the core emotions and obtained competitive results in comparison to state of the art approaches.

[1]  Marcelo Luis Errecalde,et al.  UNSL's participation at eRisk 2018 Lab , 2018, CLEF.

[2]  Fabio Crestani,et al.  eRISK 2017: CLEF Lab on Early Risk Prediction on the Internet: Experimental Foundations , 2017, CLEF.

[3]  David A. Clifton,et al.  Detecting Adolescent Psychological Pressures from Micro-Blog , 2014, HIS.

[4]  Martin D. Sykora,et al.  What about Mood Swings: Identifying Depression on Twitter with Temporal Measures of Emotions , 2018, WWW.

[5]  C. Mathers,et al.  Projections of Global Mortality and Burden of Disease from 2002 to 2030 , 2006, PLoS medicine.

[6]  A. Leenaars,et al.  Suicide Note Classification Using Natural Language Processing: A Content Analysis , 2010, Biomedical informatics insights.

[7]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[8]  Li Sun,et al.  A Depression Detection Model Based on Sentiment Analysis in Micro-blog Social Network , 2013, PAKDD Workshops.

[9]  Precha Thavikulwat,et al.  Affinity Propagation: A Clustering Algorithm for Computer-Assisted Business Simulations and Experiential Exercises , 2014 .

[10]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[11]  Karin Ackermann,et al.  The Nature Of Emotion Fundamental Questions , 2016 .

[12]  Fabio Crestani,et al.  A Test Collection for Research on Depression and Language Use , 2016, CLEF.

[13]  Sven Koitka,et al.  Linguistic Metadata Augmented Classifiers at the CLEF 2017 Task for Early Detection of Depression , 2017, CLEF.

[14]  Fabio Crestani,et al.  Overview of eRisk: Early Risk Prediction on the Internet (Extended Lab Overview) , 2018, CLEF.

[15]  Tingshao Zhu,et al.  Detecting Suicidal Ideation in Chinese Microblogs with Psychological Lexicons , 2014, 2014 IEEE 11th Intl Conf on Ubiquitous Intelligence and Computing and 2014 IEEE 11th Intl Conf on Autonomic and Trusted Computing and 2014 IEEE 14th Intl Conf on Scalable Computing and Communications and Its Associated Workshops.

[16]  Ronald C. Kessler,et al.  The burden of depressive illness , 2017 .

[17]  Sven Koitka,et al.  Word Embeddings and Linguistic Metadata at the CLEF 2018 Tasks for Early Detection of Depression and Anorexia , 2018, CLEF.

[18]  Sharath Chandra Guntuku,et al.  Detecting depression and mental illness on social media: an integrative review , 2017, Current Opinion in Behavioral Sciences.

[19]  C. Walck.  Hand-book on statistical distributions for experimentalists , 1996 .