| Presentation | 2023-07-13 Improvements in Depression Detection by Applying a Topic Model on Japanese Tweets Rio Ishibashi, Mondher Bouazizi, Tomoaki Ohtsuki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Depression is a prevalent mental health disorder that can have a significant impact on an individual's well-being. Therefore, early detection and treatment is crucial for symptom management. Recently, social media platforms have emerged as a valuable source of data for mental health research, and machine learning techniques can be employed to analyze text to identify potential signs of depression. In this study, we present a model for detecting depression based on Twitter data, which has high usage rates in Japan. We utilized the morphological analyzer Juman++ and an LDA (Latent Dirichlet Allocation) topic model to summarize Japanese tweets. User activity information was also integrated into the feature set. By testing morphological analyzers and the number of words in the dictionary, our model made improvements upon previous models [1]. Our analysis of the tweet and user features revealed that individuals with depression tend to tweet about lifestyle, work, and negative mental states. Furthermore, depressed individuals tended to post more tweets during nighttime, possibly indicating the presence of insomnia. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | depression detection / Japanese / social media / topic modeling |
| Paper # | SeMI2023-29 |
| Date of Issue | 2023-07-05 (SeMI) |
| Conference Information | |
| Committee | SeMI / RCS / RCC / NS / SR |
|---|---|
| Conference Date | 2023/7/12(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Osaka University Nakanoshima Center + Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Distributed Wireless Network, M2M (Machine-to-Machine)，D2D (Device-to-Device)，IoT（Internet of Things）, etc |
| Chair | Kazuya Monden(Hitachi) / Kenichi Higuchi(Tokyo Univ. of Science) / Shunichi Azuma(Kyoto Univ.) / Tetsuya Oishi(NTT) / Osamu Takyu(Shinshu Univ.) |
| Vice Chair | Yasunori Owada(NICT) / Shunsuke Saruwatari(Osaka Univ.) / Fumihide Kojima(NICT) / Osamu Muta(Kyushu Univ.) / Naoto Ishii(NEC) / Shunichi Azuma(Hokkaido Univ.) / Koji Ishii(Kagawa Univ.) / Takumi Miyoshi(Shibaura Inst. of Tech.) / Kentaro Ishidu(NICT) / Kazuto Yano(ATR) / Shusuke Narieda(Mie Univ.) |
| Secretary | Yasunori Owada(NTT DOCOMO) / Shunsuke Saruwatari(Tokyo Univ. of Agri. and Tech.) / Fumihide Kojima(Univ. of Tokyo) / Osamu Muta(Univ. of Electro-Comm) / Naoto Ishii(Sharp) / Shunichi Azuma(Mitsubishi Electric) / Koji Ishii(CRIEPI) / Takumi Miyoshi(Ritsumeikan Univ.) / Kentaro Ishidu(NTT) / Kazuto Yano(Kogakuin Univ.) / Shusuke Narieda(Tokai Univ.) |
| Assistant | Yuki Matsuda(NAIST) / Taku Suzuki(Hitachi) / Takeshi Hirai(Osaka Univ.) / Masashi Iwabuchi(NTT) / Issei Kanno(KDDI Research) / Yuyuan Chang(Tokyo Inst. of Tech) / Kazuki Maruta(Tokyo Univ. of Science) / Kiichi Tateishi(NTT Docomo) / SHAN LIN(NICT) / Ryosuke Adachi(Yamaguchi Univ.) / Hiroshi Yamamoto(NTT) / Taichi Ohtsuji(NEC) / WANG Xiaoyan(Ibaraki Univ.) / Akemi Tanaka(MathWorks) / Katsuya Suto(Univ. of Electro-Comm) |
| Paper Information | |
| Registration To | Technical Committee on Sensor Network and Mobile Intelligence / Technical Committee on Radio Communication Systems / Technical Committee on Reliable Communication and Control / Technical Committee on Network Systems / Technical Committee on Smart Radio |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improvements in Depression Detection by Applying a Topic Model on Japanese Tweets |
| Sub Title (in English) | |
| Keyword(1) | depression detection |
| Keyword(2) | Japanese |
| Keyword(3) | social media |
| Keyword(4) | topic modeling |
| 1st Author's Name | Rio Ishibashi |
| 1st Author's Affiliation | Keio University(Keio Univ.) |
| 2nd Author's Name | Mondher Bouazizi |
| 2nd Author's Affiliation | Keio University(Keio Univ.) |
| 3rd Author's Name | Tomoaki Ohtsuki |
| 3rd Author's Affiliation | Keio University(Keio Univ.) |
| Date | 2023-07-13 |
| Paper # | SeMI2023-29 |
| Volume (vol) | vol.123 |
| Number (no) | SeMI-110 |
| Page | pp.pp.34-39(SeMI), |
| #Pages | 6 |
| Date of Issue | 2023-07-05 (SeMI) |