Mind manipulation in dialogue exploits emotional vulnerabilities via covert tactics and hidden goals. We present a fine-grained framework that (i) detects turn-level manipulation tactics and (ii) infers dialogue-level intent before issuing a final manipulation judgment. To support training and evaluation, we curate a balanced dataset of 776 dialogues (388 manipulative, 388 non-manipulative; 15520 dialogue turns) generated via a three-phase multi-agent simulation with dual verification. On this benchmark, our model achieves 84.01% accuracy for dialogue-level manipulation detection, outperforming the strongest baseline by +6.83%. It further attains 76.25% accuracy on tactic detection and 79.53% BERTScore for intent prediction. A user study on forward-simulatability shows +11.0% accuracy improvement when the tactics and intent detected by our model are provided as rationale for dialogue manipulation detection results. These results indicate that explicit, stepwise reasoning over tactics and intent yields both higher performance and actionable interpretability for proactive monitoring of manipulative conversations.

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.

Predicting the forthcoming stress is critical for stress management. In this article, we consider not only one’s posts on social media, but also learn to understand the influence of stressor/uplift events and individual's reactions to the events by constructing an event-post correlation memory network, which evolves dynamically along with the change of events impact and one’s response reflected from their posts. We further build a joint memory network for modeling the dynamics of one’s emotions incurred by stressor/uplift events, and learn one's personality traits based on linguistic words and a fuzzy neural network. We finally predict one's future stress level based on a fully-connected network with attention, where personality traits, social activeness features, and forthcoming possible events are incorporated. We construct a dataset consisting of 1138 strongly-stressed and 985 weakly-stressed users on microblog. Experimental results show that: (1) our method outperformed the baseline, delivering 81.03 percent of prediction accuracy; (2) integrating the personality traits helped increase the prediction accuracy by 3.97 percent; (3) considering forthcoming events enabled to improve the prediction accuracy by 5.81 percent; (4) strongly-stressed users tended to be more neurotic and less active on social media, complying with psychological studies; (5) data scarcity had negative influence on stress prediction and (6) the dataset that is biased towards female made the model have a better prediction accuracy on female users.

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.

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.

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.

Stress has become an important health issue with the rapid development of economy and society. The previous work has highlighted the discriminatory power of Electrocardiogram (ECG) and social media for stress detection. However, limitations exist when using single source data for stress detection. Based on the assumption that abnormal heart rate periods are usually caused by stressor or uplifting events, we present a way to integrate heart beat rates and linguistic posts on microblogs for stress detection. We first identify one's abnormal heart rate periods, and then for each such period, we pair up a temporally synchronous and highly matched abnormal posting (stressful/exciting) period detected from microblogs. Our 4-month user study with 10 volunteer college students shows that the performance of the matching between post-based detection results with ECG-based ones can achieve over 84% accuracy for stressful or exciting periods detection, and around 70% accuracy for stressor or uplifting events detection. The results also demonstrate that SDNN is the most appropriate indicators of ECG signals for daily abnormal heart rate and stress detection.

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.

Visual sentiment analysis aims to recognize emotions from visual contents. It is a very useful yet challenging task, especially when fine-grained emotions (such as love, joy, surprise, sadness, fear, anger, disgust, and anxiety) are analyzed. Existing methods based on convolutional neural networks learn sentiment representations based on global visual features, while ignoring the fact that both the local regions of the images and their relationships can have impact on sentiment representation learning. To address this limitation, in this paper, we propose a new MultiAttentive Pyramidal model (MAP) for visual sentiment analysis. The model performs pyramidal segmentation and pooling upon the visual feature blocks obtained from a fully convolutional network, aiming to extract local visual features from multiple local regions at different scales of the global image. It then implants a self-attention mechanism to mine the associations between local visual features, and achieves the final sentiment representation. Extensive experiments on six benchmark datasets show the proposed MAP model outperforms the state-of-the-art methods in visual sentiment analysis.