Towards Suicide Prevention: Early Detection of Depression on Social Media

  title={Towards Suicide Prevention: Early Detection of Depression on Social Media},
  author={V{\'i}ctor Leiva and Ana Freire},
  booktitle={International Conference on Internet Science},
  • V. LeivaAna Freire
  • Published in
    International Conference on…
    22 November 2017
  • Psychology
The statistics presented by the World Health Organization inform that 90% of the suicides can be attributed to mental illnesses in high-income countries. Besides, previous studies concluded that people with mental illnesses tend to reveal their mental condition on social media, as a way of relief. Thus, the main objective of this work is the analysis of the messages that a user posts online, sequentially through a time period, and detect as soon as possible if this user is at risk of depression… 

A Two-Level Multi-Modal Analysis for Depression Detection From Online Social Media

A two-level depression detection method is proposed in which suspected depressed individuals are identified using social media features, personality traits, temporal and sentiment analysis of user biographies and these qualities are integrated with additional linguistic and topic features to achieve an accuracy of 89%.

Quantifying the Suicidal Tendency on Social Media: A Survey

This potential manuscript elucidates the taxonomy of mental healthcare and highlights some recent attempts in examining the potential of quantifying suicidal tendency on social media data.

An Ensemble Learning Approach for the Detection of Depression and Mental Illness over Twitter Data

The project helps to identify the linguistic features of the tweets and the behavioral pattern of the Twitter users who post them, which could demonstrate symptoms of depression, by synchronizing different machine learning algorithms to work as an ensemble model for higher efficiency and accuracy.

A Review Paper: Accuracy of Machine Learning for Depression Detection in Social Media

A systematic literature review of machine learning algorithms for detecting depression found that the greatest accuracy is obtained from Logistic Regression with an accuracy value of 99.80%.

Depression Detection on Social Media with the Aid of Machine Learning Platform: A Comprehensive Survey

  • G. GuptaD. Sharma
  • Psychology
    2021 8th International Conference on Computing for Sustainable Global Development (INDIACom)
  • 2021
Depression is a group of mental disorders associated with certain factors which can affect the mood, feelings, negativity, losing interest, and sadness in human participants. To maintain the quality

Early Risk Detection of Anorexia on Social Media

A machine learning approach that processes the texts written by social media users based on a set of features based on domain-specific vocabulary, topics, psychological processes, and linguistic information extracted from the users’ writings suitable for the early detection of anorexia nervosa symptoms.

Feature Based Depression Detection from Twitter Data Using Machine Learning Techniques

The work proposed a numerical score for each user based on the sentiment value of their tweets and demonstrated that this feature can detect depression with an accuracy of 78% with the XGBoost classifier.

A review on recognizing depression in social networks: challenges and opportunities

This paper addresses the state-of-the-art regarding studies on recognition of depressive mood disorders in social networks through approaches and techniques of sentiment and emotion analysis, and the most employed techniques, feelings, and emotions were analyzed.

A review on recognizing depression in social networks: challenges and opportunities

This paper addresses the state-of-the-art regarding studies on recognition of depressive mood disorders in social networks through approaches and techniques of sentiment and emotion analysis, and the most employed techniques, feelings, and emotions were analyzed.

Detecting Presence of PTSD Using Sentiment Analysis From Text Data

This study trains a machine learning model on text data, which is part of the Audio/Visual Emotion Challenge and Workshop (AVEC-19) corpus, to identify individuals with PTSD using sentiment analysis from semi-structured interviews, and shows that learned models can use sentiment analysis of speech to identify the presence of PTSD, even through a virtual medium.



A Depression Detection Model Based on Sentiment Analysis in Micro-blog Social Network

A depression detection model is constructed based on the proposed method and 10 features of depressed users derived from psychological research, and an application is developed within the proposed model for mental health monitoring online.

Identifying Depression on Twitter

This work employs a crowdsourced method to compile a list of Twitter users who profess to being diagnosed with depression, and posits a new methodology for constructing a classifier by treating social as a text-classification problem, rather than a behavioral one on social media platforms.

Quantifying Mental Health Signals in Twitter

A novel method for gathering data for a range of mental illnesses quickly and cheaply is presented, then analysis of four in particular: post-traumatic stress disorder, depression, bipolar disorder, and seasonal affective disorder are focused on.

Depressive Moods of Users Portrayed in Twitter

A preliminary result on building a research framework that utilizes real-time moods of users captured in the Twitter social network and explore the use of language in describing depressive moods is presented.

A content analysis of depression-related tweets

Grief-Stricken in a Crowd: The Language of Bereavement and Distress in Social Media

This paper presents a coding system for identifying emotion distressed content, followed by a detailed analysis of language use that lays a foundation for natural language processing (NLP) tasks, such as automatic detection of bereavement-related distress.

Brief report: preliminary results of a suicide awareness mass media campaign in Cuyahoga County, Ohio.

Examination of the pattern of calls before, during, and between phases of the campaign suggests that the media campaign significantly increased telephone calls to the emergency service in Cuyahoga County, Ohio.

Longitudinal and Incremental Relation of Cybervictimization to Negative Self-Cognitions and Depressive Symptoms in Young Adolescents

Over and above conventional types of peer victimization, CV significantly predicted changes in self-referential negative cognitions, victimization-related cognitive reactions, and depressive symptoms, even after controlling for baseline levels of the dependent variables.

VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text

Interestingly, using the authors' parsimonious rule-based model to assess the sentiment of tweets, it is found that VADER outperforms individual human raters, and generalizes more favorably across contexts than any of their benchmarks.

A statistical interpretation of term specificity and its application in retrieval

It is argued that terms should be weighted according to collection frequency, so that matches on less frequent, more specific, terms are of greater value than matches on frequent terms.