Automatic Profiles Collection from Twitter Users with Depressive Symptoms.

Mental illness is a pressing issue that needs urgent attention, as the number of people suffering from mental disorders continues to increase. Diagnosing mental health disorders can be challenging, and gathering information about a patient's medical history and symptoms is crucial for an accurate diagnosis. Self-disclosure on social media can provide valuable insights into whether users may be suffering from a mental illness. This paper proposes a method for automatically collecting data from social media users who disclosed their depression. The proposed approach yielded a 97% accuracy rate with a majority of 95%.

Deep Learning With Anaphora Resolution for the Detection of Tweeters With Depression: Algorithm Development and Validation Study.

BACKGROUND: Mental health problems are widely recognized as a major public health challenge worldwide. This concern highlights the need to develop effective tools for detecting mental health disorders in the population. Social networks are a promising source of data wherein patients publish rich personal information that can be mined to extract valuable psychological cues; however, these data come with their own set of challenges, such as the need to disambiguate between statements about oneself and third parties. Traditionally, natural language processing techniques for social media have looked at text classifiers and user classification models separately, hence presenting a challenge for researchers who want to combine text sentiment and user sentiment analysis. OBJECTIVE: The objective of this study is to develop a predictive model that can detect users with depression from Twitter posts and instantly identify textual content associated with mental health topics. The model can also address the problem of anaphoric resolution and highlight anaphoric interpretations. METHODS: We retrieved the data set from Twitter by using a regular expression or stream of real-time tweets comprising 3682 users, of which 1983 self-declared their depression and 1699 declared no depression. Two multiple instance learning models were developed-one with and one without an anaphoric resolution encoder-to identify users with depression and highlight posts related to the mental health of the author. Several previously published models were applied to our data set, and their performance was compared with that of our models. RESULTS: The maximum accuracy, F1 score, and area under the curve of our anaphoric resolution model were 92%, 92%, and 90%, respectively. The model outperformed alternative predictive models, which ranged from classical machine learning models to deep learning models. CONCLUSIONS: Our model with anaphoric resolution shows promising results when compared with other predictive models and provides valuable insights into textual content that is relevant to the mental health of the tweeter.

Public Opinions on Using Social Media Content to Identify Users With Depression and Target Mental Health Care Advertising: Mixed Methods Survey.

BACKGROUND: Depression is a common disorder that still remains underdiagnosed and undertreated in the UK National Health Service. Charities and voluntary organizations offer mental health services, but they are still struggling to promote these services to the individuals who need them. By analyzing social media (SM) content using machine learning techniques, it may be possible to identify which SM users are currently experiencing low mood, thus enabling the targeted advertising of mental health services to the individuals who would benefit from them. OBJECTIVE: This study aimed to understand SM users' opinions of analysis of SM content for depression and targeted advertising on SM for mental health services. METHODS: A Web-based, mixed methods, cross-sectional survey was administered to SM users aged 16 years or older within the United Kingdom. It asked participants about their demographics, their usage of SM, and their history of depression and presented structured and open-ended questions on views of SM content being analyzed for depression and views on receiving targeted advertising for mental health services. RESULTS: A total of 183 participants completed the survey, and 114 (62.3%) of them had previously experienced depression. Participants indicated that they posted less during low moods, and they believed that their SM content would not reflect their depression. They could see the possible benefits of identifying depression from SM content but did not believe that the risks to privacy outweighed these benefits. A majority of the participants would not provide consent for such analysis to be conducted on their data and considered it to be intrusive and exposing. CONCLUSIONS: In a climate of distrust of SM platforms' usage of personal data, participants in this survey did not perceive that the benefits of targeting advertisements for mental health services to individuals analyzed as having depression would outweigh the risks to privacy. Future work in this area should proceed with caution and should engage stakeholders at all stages to maximize the transparency and trustworthiness of such research endeavors.

Modeling Depression Symptoms from Social Network Data through Multiple Instance Learning.

Mental health issues are widely accepted as one of the most prominent health challenges in the world, with over 300 million people currently suffering from depression alone. With massive volumes of user-generated data on social networking platforms, researchers are increasingly using machine learning to determine whether this content can be used to detect mental health problems in users. This study aims to develop a deep learning model to classify users with depression via multiple instance learning, which can learn from user-level labels to identify post-level labels. By combining every possibility of posts label category, it can generate temporal posting profiles which can then be used to classify users with depression. This paper shows that there are clear differences in posting patterns between users with depression and non-depression, which is represented through the combined likelihood of posts label category.

Researching Mental Health Disorders in the Era of Social Media: Systematic Review.

BACKGROUND: Mental illness is quickly becoming one of the most prevalent public health problems worldwide. Social network platforms, where users can express their emotions, feelings, and thoughts, are a valuable source of data for researching mental health, and techniques based on machine learning are increasingly used for this purpose. OBJECTIVE: The objective of this review was to explore the scope and limits of cutting-edge techniques that researchers are using for predictive analytics in mental health and to review associated issues, such as ethical concerns, in this area of research. METHODS: We performed a systematic literature review in March 2017, using keywords to search articles on data mining of social network data in the context of common mental health disorders, published between 2010 and March 8, 2017 in medical and computer science journals. RESULTS: The initial search returned a total of 5386 articles. Following a careful analysis of the titles, abstracts, and main texts, we selected 48 articles for review. We coded the articles according to key characteristics, techniques used for data collection, data preprocessing, feature extraction, feature selection, model construction, and model verification. The most common analytical method was text analysis, with several studies using different flavors of image analysis and social interaction graph analysis. CONCLUSIONS: Despite an increasing number of studies investigating mental health issues using social network data, some common problems persist. Assembling large, high-quality datasets of social media users with mental disorder is problematic, not only due to biases associated with the collection methods, but also with regard to managing consent and selecting appropriate analytics techniques.