12 pages, 3 figures and 3 tables. Accepted in 20th International Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2019. To be published in Springer LNCS volume
Expressing the polarity of sentiment as 'positive' and 'negative' usually have limited scope compared with the intensity/degree of polarity. These two tasks (i.e. sentiment classification and sentiment intensity prediction) are closely related and may offer assistance to each other during the learning process. In this paper, we propose to leverage the relatedness of multiple tasks in a multi-task learning framework. Our multi-task model is based on convolutional-Gated Recurrent Unit (GRU) framework, which is further assisted by a diverse hand-crafted feature set. Evaluation and analysis suggest that joint-learning of the related tasks in a multi-task framework can outperform each of the individual tasks in the single-task frameworks.
Social media are pervasive in our life, making it necessary to ensure safe online experiences by detecting and removing offensive and hate speech. In this work, we report our submission to the Offensive Language and hate-speech Detection shared task organized with the 4th Workshop on Open-Source Arabic Corpora and Processing Tools Arabic (OSACT4). We focus on developing purely deep learning systems, without a need for feature engineering. For that purpose, we develop an effective method for automatic data augmentation and show the utility of training both offensive and hate speech models off (…
AI shares emotion with humans across languages and cultures
University of Science and Technology of China（中国科学技术大学）；Peking University（北京大学）；Tsinghua University（清华大学）；Beijing Normal University（北京师范大学）；The Hong Kong Polytechnic University（香港理工大学）；The PolyU-Hangzhou Technology and Innovation Research Institute（香港理工大学杭州科技创新研究院）；Changping Laboratory（昌平实验室）
Affective Computing Has Changed: The Foundation Model Disruption
Technical University of Munich（慕尼黑工业大学）；Munich Data Science Institute（慕尼黑数据科学研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Imperial College London（伦敦帝国学院）；University of Augsburg（奥格斯堡大学）；Universidad Autonoma de Madrid（马德里自治大学）；SyncPilot GmbH（SyncPilot有限公司）
Snap Inc.（色拉布公司）；Ecole Polytechnique, IP Paris（巴黎综合理工学院（巴黎理工学院））；Stanford University（斯坦福大学）
In this work, we explore the emotional reactions that real-world images tend to induce by using natural language as the medium to express the rationale behind an affective response to a given visual stimulus. To embark on this journey, we introduce and share with the research community a large-scale dataset that contains emotional reactions and free-form textual explanations for 85,007 publicly available images, analyzed by 6,283 annotators who were asked to indicate and explain how and why they felt in a particular way when observing a specific image, producing a total of 526,749 responses. E…
Multi-domain sentiment classification deals with the scenario where labeled data exists for multiple domains but insufficient for training effective sentiment classifiers that work across domains. Thus, fully exploiting sentiment knowledge shared across domains is crucial for real world applications. While many existing works try to extract domain-invariant features in high-dimensional space, such models fail to explicitly distinguish between shared and private features at text-level, which to some extent lacks interpretablity. Based on the assumption that removing domain-related tokens from t…
Idiap Research Institute（伊迪亚普研究所）；Yahoo Inc.（雅虎公司）；JW Player（JW Player公司）；Columbia University（哥伦比亚大学）
The impact of culture in visual emotion perception has recently captured the attention of multimedia research. In this study, we pro- vide powerful computational linguistics tools to explore, retrieve and browse a dataset of 16K multilingual affective visual concepts and 7.3M Flickr images. First, we design an effective crowdsourc- ing experiment to collect human judgements of sentiment connected to the visual concepts. We then use word embeddings to repre- sent these concepts in a low dimensional vector space, allowing us to expand the meaning around concepts, and thus enabling insight about …
Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we propose two deep architectures which can be trained jointly on multiple related tasks. More specifically, we augment neural model with an external memory, which is shared by several tasks. Experiments on two groups of text classification tasks show that our proposed architectures can improve the performance of a task with the help of…
Automated Detection and Classification of Delusion-related Content in Naturalistic Audio Diaries Using Multi-Agent Language Models
Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, USA（生物医学信息学与医学教育系，华盛顿大学，西雅图，华盛顿州，美国）；Department of Psychiatry and Behavioral Sciences, University of Washington, Seattle, WA, USA（精神病学与行为科学系，华盛顿大学，西雅图，华盛顿州，美国）；Department of Psychology, Louisiana State University, Baton Rouge, LA, USA（心理学系，路易斯安那州立大学，巴吞鲁日，路易斯安那州，美国）；Department of Psychiatry, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA（精神病学系，北卡罗来纳大学教堂山分校，教堂山，北卡罗来纳州，美国）
The COVID-19 pandemic has introduced new opportunities for health communication, including an increase in the public use of online outlets for health-related emotions. People have turned to social media networks to share sentiments related to the impacts of the COVID-19 pandemic. In this paper we examine the role of social messaging shared by Persons in the Public Eye (i.e. athletes, politicians, news personnel) in determining overall public discourse direction. We harvested approximately 13 million tweets ranging from 1 January 2020 to 1 March 2022. The sentiment was calculated for each tweet…
