Leverage Social Media for Personalized Stress Detection

Abstract

Timely detection of stress is desirable to address the increasingly serious stress problem. Thanks to the rich linguistic expressions and complete historical records on social media, achieving personalized stress detection through social media is feasible and prominent. We construct a three-leveled framework, aiming at personalized stress detection based on social media. The three-leveled framework learns the personalized stress representations following an increasingly detailed processing, i.e., from the generic mass level, group level, to the final individual level. The first mass-level focuses on mining the generic stress representations from people's linguistic and visual posts with a two-layer attention mechanism. The second group-level adopts the graph neural network to learn the groupwise characteristics of the group where an individual belongs to. The third individual-level analyzes and incorporates individual's personality traits into stress detection. The performance study on the 2,059 microblog users shows that our proposed method can achieve over 90% in detection accuracy. Furthermore, the extended experiment on a harder personalized sub-dataset demonstrates that our method works better in distinguishing personalized expressions with different latent meanings. CCS CONCEPTS • Applied computing → Psychology; • Human-centered computing → Social media; • Information systems → Sentiment analysis.

Exploring Emotional Stimuli Detection in Artworks: A Benchmark Dataset and Baselines Evaluation

“…Visual emotion analysis Given an input image, visual emotion analysis aims to recognize emotions, analyze the emotional stimuli, and apply the recognized emotions to real-world applications (e.g., psychological health [25,26] and opinion mining [27,28]) to improve the ability of emotional intelligence [29]. Most of the recent studies [17][18][19][20][21] use emotional stimuli to improve emotion recognition, but only a few efforts have been made to analyze how well the models detect such stimuli.…”

TranSentGAT: A Sentiment-Based Lexical Psycholinguistic Graph Attention Network for Personality Prediction

“…According to its theory, personality may be broken down to five main characteristics, abbreviated as CANOE or OCEAN: Conscientiousness, Agreeableness, Neuroticism, Openness and Extraversion. Developing an architecture to predict the users' personality traits automatically from their shared content in social media can have many applications such as recommendation systems [6], psychological studies [7,8], forensics [9], intelligent machine design [10], etc. [11].…”

Análise do estresse e tópicos discutidos no Twitter durante a pandemia da COVID-19 no Brasil

“…Também existem diversos trabalhos na literatura com o objetivo de prever o nível de estresse dos usuários por meio de técnicas de minerac ¸ão de textos publicados nas redes sociais, como no caso de [Lin et al 2014] e [Wang et al 2020]. [Lin et al 2014] pesquisaram a aplicac ¸ão de um modelo baseado em redes neurais profundas para detectar de forma automática o estresse psicológico dos usuários por meio das redes sociais.…”