Collocated with IE 2023 - 19th International Conference on Intelligent Environments
The 2nd International Workshop on Sentiment Analysis and Emotion Recognition aims to enable synergy among key aspects, such as how to manage the sensory capacity of robots to gather the information needed, how to improve machine learning techniques to be suitable for social robots, and how to manage different modalities with efficient fusion methods. This workshop provides a venue for members from a range of international institutions, including universities, research labs, and industry to exchange ideas and experiences, analyze, present, and discuss latest research and development issues, and propose theoretical foundations related to research on combining solutions for developing efficient and suitable solutions for emotion and sentiment detection for social robots. This synergistic focus will enforce the engineering of intelligent and innovative solutions in this regard to guide their design and to promote the development of new approaches (architectures, tools, and models) of emotion/sentiment recognition for social robots.
Univ. Internacional de Valencia, Spain
Univ. Católica San Pablo, Peru
Univ. de Valparaíso, Chile
Univ. Católica San Pablo, Peru
Univ. Bordeaux - ESTIA, France
Universidad de Extremadura, Spain
Paper Submission: March 1st, 2023
Notification of Acceptance: April 5th, 2023
Camera Ready: April 15th, 2023
Prospective authors are encouraged to submit papers for evaluation by the Program Committee. All submissions will be peer-reviewed by at least 3 peer reviewers with expertise in the area. This process will result in constructive feedback to the authors and the selection of the best contributions to be presented in the workshop and published in the proceedings. After the preliminary notification date, authors rebut by evidence and arguments all reviewer inquiries and their comments. Based on the rebuttal feedback, reviewers notify authors with the final decision. Selection criteria will include: relevance, significance, impact, originality, technical soundness, and quality of presentation. Preference will be given to submissions that take strong or challenging positions on important emergent topics related to the workshop. At least one author should attend the workshop to present the paper.
All papers accepted for publication must follow the formatting rules for Springer Proceedings (https://www.iospress.com/book-article-instructions) and be written in English, with a length of at least 6 but no more than 10 pages. Latex and Word templates can be found in http://www.iospress.nl/service/authors/latex-and-word-tools-for-book-authors.
Important note for double blind review policy: The version of papers for evaluation by the Program Committee, saved in PDF format, must not include identification, e-mail, affiliation of the authors, grants, funding institution or any explicit information, that may disclose the authors’ identity (this information is to be restored in the camera-ready version upon acceptance). Please remove author names and affiliations (or replace it with Xs) on submitted papers. In particular, in the version submitted for review please avoid explicit auto-references, such as “as we shown in ” — consider “as shown in “. i.e., you may cite your own previous works provided that it is not deducible from the text that the cited work belongs to the authors. This information must only be available in the camera-ready version of accepted papers, saved in Word or Latex format and also in PDF format. These files must be accompanied by the Consent to Publish form filled out, in a ZIP file, and uploaded at the conference management system.
The submission system for this workshop is based on EasyChair. To submit or upload a paper please go to https://easychair.org/conferences/?conf=sentirobots2023.
All papers accepted in the Workshops program will be published as a volume of the Ambient Intelligence and Smart Environments Series of IOS Press and electronically available through ACM Digital Library (pending approval). The proceedings will be ISI indexed.
Erik Cambria is the Founder of SenticNet, a Singapore-based company offering B2B sentiment analysis services, and an Associate Professor at NTU, where he also holds the appointment of Provost Chair in Computer Science and Engineering. Prior to joining NTU, he worked at Microsoft Research Asia (Beijing) and HP Labs India (Bangalore) and earned his PhD through a joint programme between the University of Stirling and MIT Media Lab. His research focuses on neurosymbolic AI for explainable natural language processing in domains like sentiment analysis, dialogue systems, and financial forecasting. He is recipient of several awards, e.g., IEEE Outstanding Career Award, was listed among the AI's 10 to Watch, and was featured in Forbes as one of the 5 People Building Our AI Future. He is Associate Editor of many top AI journals, e.g., INFFUS, IEEE CIM, and AIRE, Department Editor of IEEE Intelligent Systems (ACSA), and is involved in various international conferences.
Emotion recognition in conversation (ERC) has received increasing attention from the research community. However, the ERC task is challenging, largely due to the complex and unstructured properties of multi-party conversations. Besides, the majority of daily dialogues take place in a specific context or circumstance, which requires rich external knowledge to understand the background of a certain dialogue. In this paper, we address these challenges by explicitly modeling the discourse relations between utterances and incorporating symbolic knowledge into multi-party conversations. We first introduce a dialogue parsing algorithm into ERC and further improve the algorithm through a transfer learning method. Moreover, we leverage different symbolic knowledge graph relations to learn knowledge-enhanced features for the ERC task. Extensive experiments on three benchmarks demonstrate that both dialogue structure graphs and symbolic knowledge are beneficial to the model performance on the task. Additionally, experimental results indicate that the proposed model surpasses baseline models on several indices.