Stress haunts people in modern society, which may cause severe health issues if left unattended. With social media becoming an integral part of daily life, leveraging social media to detect stress has gained increasing attention. While the majority of the work focuses on classifying stress states and stress categories, this study introduce a new task aimed at estimating more specific stressors (like exam, writing paper, etc.) through users' posts on social media. Unfortunately, the diversity of stressors with many different classes but a few examples per class, combined with the consistent arising of new stressors over time, hinders the machine understanding of stressors. To this end, we cast the stressor estimation problem within a practical scenario few-shot learning setting, and propose a novel meta-learning based stressor estimation framework that is enhanced by a meta-knowledge inheritance mechanism. This model can not only learn generic stressor context through meta-learning, but also has a good generalization ability to estimate new stressors with little labeled data. A fundamental breakthrough in our approach lies in the inclusion of the meta-knowledge inheritance mechanism, which equips our model with the ability to prevent catastrophic forgetting when adapting to new stressors. The experimental results show that our model achieves state-of-the-art performance compared with the baselines. Additionally, we construct a social media-based stressor estimation dataset that can help train artificial intelligence models to facilitate human well-being.

Suicide presents a global health challenge, prompting the development of diverse prevention strategies. Among them, timely identification of individuals at risk of suicide remains challenging. Although social media offers potential for tracking users’ mental status, harnessing collaboration between AI and human experts for real-time prediction of suicide risk is inadequately explored. This study presents a human-in-the-loop framework for real-time suicide risk prediction based on social media. Once a user made a new post on social media, the AI model assesses user’s suicide risk within the next month with explanation based on the historic and new posts plus domain knowledge. Human experts on the other side look into the explanation to confirm/clarify uncertain information as feedback, enabling consistent evolution of the model. Experiments on the constructed dataset, containing 66 suicidal users and 66 non-suicidal users, show that our method achieved 82.58% prediction accuracy, outperforming competitive baselines by 6.57%. Leveraging human feedback improved prediction accuracy by 4.12%. Consultation with 18 experts (including 6 medical staff and 12 psychologists) was conducted to examine the validity of our method. Ethics considerations, as well as potential and limitations of large language models in mental condition prediction, are also discussed at the end of the paper.

Multimodal hate detection plays a crucial role in maintaining harmonious online environments by identifying harmful content, such as hateful memes. Although previous research has made significant progress in detecting explicit hate speech, there remains a critical gap in analyzing implicit hate, which is particularly challenging due to the absence of explicit harmful text claims or demographic visual cues. Despite the promising results based on cross-modal attention, previous methods may suffer from the distributional modality gap caused by the non-literal associations between multimodal elements, which lacks apparent alignment in implicit hateful contents. In this work, we propose a novel framework: Flexible Optimal Transport (FLOT) to capture the non-literal cross-modal alignment for multimodal hate in the context of memes. FLOT formulates the problem of cross-modal alignment as finding optimal transportation plans, which leverages a kernel method to capture complementary information from multiple modalities. The kernel embeddings reproduce a kernel Hilbert space (RKHS) to serve as a non-linear transformation of alignment, which effectively reduces the distributional modality gap with more interpretability. Moreover, we established topological structures with contrastive modeling for the aligned representations, which are optimized to achieve comprehensive alignment between different modalities, and facilitate local reasoning based on multimodal elements. Experimental results have demonstrated that our FLOT achieved state-of-the-art performance on three publicly available benchmark datasets. Furthermore, extensive qualitative analysis confirms the superior ability of FLOT in capturing implicit cross-modal alignment.

Predicting stress can help people take timely action to manage stress before potential physical and psychological problems arise. In this study, we analyze and verify chaotic features of human's stress response to stressor and uplift events, and present an event–behavior–stress triangle model for stress prediction. We reconstruct the phase space based on chaos theory, and integrate stress-correlated pre and postfactors (events and behaviors) through an event–behavior–stress correlation memory and a behavior-stress correlation memory for stress prediction. User's personal features (including self-cognition, opinion about school, personality traits, and future event's impact) are also involved in stress prediction. We conduct the experiments on the publicly available StudentLife dataset collected from a mobile phone app, including users’ daily activities inferred through the automatic and continuous sensing application and users’ self-reported ecological momentary assessments (EMA) data. The experimental results show that the proposed method outperforms four baseline methods, achieving (88.13% accuracy, 79.38% precision, 77.10% recall, 78.19% F1-score) for 2-labeled (nonstressed/stressed) stress prediction, and (70.42% accuracy, 69.21% precision, 67.90% recall, 68.53% F1-score) for 3-label (nonstressed/little-stressed/huge-stressed) stress prediction. Further possible improvements and implications related to chaos-based stress prediction are also discussed at the end of the article.https://github.com/lny0806/chaos-stress-predict

Detecting stress via user's social media posts has attracted increasing research interests in recent years. The majority of the methods leverage word embeddings to represent each of the posted words as a vector, and then perform classification on a sequence of word vectors. To enhance the performance of distinguishing words/phrases related to stressors and stressful emotions from others, in this study, we present a stress-specific word embedding learning framework upon the pre-trained language model BERT. Specifically, we formulate three self-supervised contrastive learning tasks with a joint learning objective. (1) The stressor discrimination task, which is designed to allow the framework to be sensitive to words/phrases about stressors. (2) The stressor cluster discrimination task, which is designed to allow the framework to distinguish stressors into different categories. (3) The stressful emotion discrimination task, which is designed to allow the framework to grasp words/phrases about stressful emotions. Our performance study shows that the learned stress-specific word embedding can significantly benefit social media based stress detection tasks, especially in the more practical scenarios with insufficient labeled data. Besides, we build two user-level social media based stress detection datasets that can help train machine learning models to facilitate human well-being.

Suicide has become a serious problem, hurting the well-being of human society. Thanks to social media, from people's linguistic posts, suicide risk detection has achieved good performance. The aim of this article is to investigate whether more significant accuracy could be achieved. Motivated by the observation that the prior solutions strived to detect suicide risk based on users explicit outer post expressions on social media, and no attempt was made to infer users’ inner true thoughts and emotion changes from their normal open posts for suicide risk detection, we propose to first learn the correlations between user's normal open posts and hidden comments, trying to understand user's inner true thoughts and emotion changes from the open posts, and then detect user's suicide risk upon the generated intermediate results. The better detection performance on the microblog dataset (3,652 at-risk microblog users and 3,652 ordinary microblog users) and forum dataset (392 at-risk forum users and 108 ordinary forum users) verifies the insight that it is more effective to learn users’ inner thoughts and emotion changes for social media-based suicide risk detection.

Leveraging social media for stress detection has been growing attention in recent years. Most relevant studies so far concentrated on training a stress detection model on the entire data in a closed environment, and did not continuously incorporate new information into the already established models but instead regularly reconstruct a new model from scratch. In this study, we formulate a social media based continuous stress detection task with two particular questions to be addressed: (1) when to adapt a learned stress detection model? and (2) how to adapt a learned stress detection model? We design a protocol to quantify the conditions that trigger model's adaptation, and develop a layer-inheritance based knowledge distillation method to continually adapt the learned stress detection model to incoming data, while retaining the knowledge gained previously. The experimental results on a constructed dataset containing 69 users on Tencent Weibo validate the effectiveness of the proposed adaptive layer-inheritance based knowledge distillation method, achieving 86.32% and 91.56% of accuracy in 3-label and 2-label continuous stress detection. Implications and further possible improvements are also discussed at the end of the article.

Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) self-supervised EA approach draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, it advocates the minimum information requirement for self-supervised EA, while we argue that self-described KG's side information (e.g., entity name, relation name, entity description) shall preferably be explored to the maximum extent for the self-supervised EA task. In this work, we propose an interactive contrastive learning model for self-supervised EA. It conducts bidirectional contrastive learning via building pseudo-aligned entity pairs as pivots to achieve direct cross-KG information interaction. It further exploits the integration of entity textual and structural information and elaborately designs encoders for better utilization in the self-supervised setting. Experimental results show that our approach outperforms the previous best self-supervised method by a large margin (over 9% [email protected] absolute improvement on average) and performs on par with previous SOTA supervised counterparts, demonstrating the effectiveness of the interactive contrastive learning for self-supervised EA. The code and data are available at https://github.com/THU-KEG/ICLEA.

Psychological stress has become a wider-spread and serious health issue in modern society. Detecting stressors that cause the stress could enable people to take effective actions to manage the stress. Previous work relied on the stressor dictionary built upon words from the stressor-related categories in the LIWC (Linguistic Inquiry and Word Count), and focused on stress categories that appear frequently on social media. In this paper, we build a meta-learning based stress category detection framework, which can learn how to distinguish a new stress category with very little data through learning on frequently appeared categories without relying on any lexicon. It is comprised of three modules, i.e., encoder module, induction module, and relation module. The encoder module focuses on learning category-relevant representation of each tweet with Dependency Graph Convolutional Network and tweet attention. The induction module deploys Mixture of Experts mechanism to integrate and summarize a representation for each category. The relation module is adopted to measure the correlation between each pair of query tweets and categories. Through the three modules and the meta-training process, we can then obtain a model which learns to learn how to identify stress categories and can directly be employed to a new category with little labelled data. Our experimental results show that the proposed framework can achieve 75.3 accuracy with 3 labeled data for the rarely appeared stress categories. We also build a stress category dataset consisting of 12 stress categories with 1,553 manually labeled stressful microblogs which can help train AI models to assist psychological stress diagnosis.

Automated deception detection has been found as a vital and concerned task, capable of assisting human users to assess truthfulness and detect deceptive behaviors in several situations (e.g., medical, legal, as well as occupational domains). As contact-free video cameras and data analysis techniques are leaping forward, leveraging one’s visual, acoustic and textual information captured in a video can be cost-effective for deception detection. In this study, we aim at a fine-grained question-level deception detection task, focusing on detecting whether a subject lies or not in answering each question rather than providing an overall “lie or not” judgement. A Graph-based Cross-modal Fusion Model (GCFM) is presented to learn the inherent associations among the subject’s reactions to different questions, plus a novel cross-modal attention mechanism to enhance the model’s learning capability. As revealed by the experimental results on the two datasets, the proposed graph-based GCFM outperformed eight other methods, and its two alternatives (clustering K-means based and sequential learning LSTM based methods), achieving accuracy 88.14% and 86.91% on the two datasets, respectively. Besides, through association learning, GCFM could increase the accuracy by 1.87% and 4.33% on the two datasets, respectively. Furthermore, its cross-modal attention mechanism led to the improvement of accuracy by 2.44% and 2.95% on the two datasets, respectively.

People today live a stressful life. Compared with acute stress, long-term chronic stress is more harmful, and may cause or exacerbate many serious health problems, including high blood pressure, heart disease, chronic pain, and mental diseases. With social media becoming an integral part of our daily lives for information sharing and self-expression, detecting category-aware long-standing chronic stress from a large volume of historic open posts made by social media users is possible. In this study, we construct a data set containing 971 chronically stressed users with totally 54 546 open posts on Sina microblog from July 5, 2018 to December 1, 2019, and design two techniques for category-aware chronic stress detection: (1) a stress-oriented word embedding on the basis of an existing pre-trained word embedding, aiming to strengthen the sensibility of stress-related expressions for linguistic post analysis; (2) a multi-attention model with three layers (i.e., category-attention layer, posts self-attention layer, and category-specific post attention layer), aiming to capture inter-relevance from a sequence of posts and infer long-term stress categories and stress levels. The experimental results show that the proposed multi-attention model equipped with the stress-oriented word embedding can achieve 80.65% accuracy in detecting category-aware stress levels, 86.49% accuracy in detecting chronic stress levels only, and 93.07% accuracy in detecting chronic stress categories only. Limitations and implications of the study are also discussed at the end of the paper.

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 group-wise 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.

Lei Cao, Huijun Zhang, Ling Feng, Zihan Wei, Xin Wang, Ningyun Li, Xiaohao He. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.