Research Area:  Machine Learning

Abstract:

Depression is a common mental health disorder. Despite its high prevalence, the only way of diagnosing depression is through self-reporting. However, 70% of the patients would not consult doctors at an early stage of depression. Meanwhile people increasingly relying on social media for sharing emotions, and daily life activities thus helpful for detecting their mental health. Inspired by these a total of 179 depressive individuals selected from Twitter, who have reported depression and they are on medical treatment. A sample of their recent tweets collected ranges from (200 to 3200) tweets per person. From their tweets, we selected 100 most frequently used words using Term Frequency-Inverse Document Frequency (TF-IDF). Later, we used the 14 psychological attributes in Linguistic Inquiry and Word Count (LIWC) to classify these words into emotions. Moreover, weights were assigned to each word from happy to unhappy after classification by LIWC and trained machine learning classifiers to classify the users into three classes of depression High, Medium, and Low. According to our study, better features selections and their combination will help to improve performance and accuracy of classifiers.

Keywords:  

Author(s) Name:  Raza Ul MustafaNoman AshrafFahad Shabbir AhmedJaved FerzundBasit ShahzadAlexander Gelbukh

Publisher name:  Springer

DOI:  https://doi.org/10.1007/978-3-030-43020-7_89

Volume Information:  

Paper Link:   https://link.springer.com/chapter/10.1007/978-3-030-43020-7_89