Detecting Depression Signs on Social Media: A Systematic Literature Review.

Among mental health diseases, depression is one of the most severe, as it often leads to suicide; due to this, it is important to identify and summarize existing evidence concerning depression sign detection research on social media using the data provided by users. This review examines aspects of primary studies exploring depression detection from social media submissions (from 2016 to mid-2021). The search for primary studies was conducted in five digital libraries: ACM Digital Library, IEEE Xplore Digital Library, SpringerLink, Science Direct, and PubMed, as well as on the search engine Google Scholar to broaden the results. Extracting and synthesizing the data from each paper was the main activity of this work. Thirty-four primary studies were analyzed and evaluated. Twitter was the most studied social media for depression sign detection. Word embedding was the most prominent linguistic feature extraction method. Support vector machine (SVM) was the most used machine-learning algorithm. Similarly, the most popular computing tool was from Python libraries. Finally, cross-validation (CV) was the most common statistical analysis method used to evaluate the results obtained. Using social media along with computing tools and classification methods contributes to current efforts in public healthcare to detect signs of depression from sources close to patients.

Sentiment Analysis on Tweets about Diabetes: An Aspect-Level Approach.

In recent years, some methods of sentiment analysis have been developed for the health domain; however, the diabetes domain has not been explored yet. In addition, there is a lack of approaches that analyze the positive or negative orientation of each aspect contained in a document (a review, a piece of news, and a tweet, among others). Based on this understanding, we propose an aspect-level sentiment analysis method based on ontologies in the diabetes domain. The sentiment of the aspects is calculated by considering the words around the aspect which are obtained through N-gram methods (N-gram after, N-gram before, and N-gram around). To evaluate the effectiveness of our method, we obtained a corpus from Twitter, which has been manually labelled at aspect level as positive, negative, or neutral. The experimental results show that the best result was obtained through the N-gram around method with a precision of 81.93%, a recall of 81.13%, and an F-measure of 81.24%.