Sixth International Workshop on eXplainable SENTIment Mining and EmotioN deTection Hersonissos, Greece, June 7 2021 - moved online
Proceedings
The Sixth International Workshop on eXplainable SENTIment Mining and
EmotioN deTection (X-SENTIMENT 2021)1 was held as part of the 18th Extended
Semantic Web Conference on June 7, 2021. X-SENTIMENT 2021 was expected
to happen in Hersonissos, Greece, but due to the COVID-19 emergency and
the consequent travel restrictions, the workshop was held online. During the
years, the workshop around the Sentiment Analysis and Emotion Detection
topics changed its title based on the emphasis it was decided to give to timely
research interests of the community [
The workshop collected novel, original research on the state of the art of explainability targeting sentiment analysis and emotion detection empowered with Natural Language Processing (NLP), Knowledge Graphs (KGs), and Machine Learning (ML), providing a common ground for researchers, practitioners, and stakeholders working in this area. The workshop day included three paper presentations and a keynote talk to highlight open issues, research challenges, and future research directions. More than 20 participants were registered and attended the workshop.
Overall, 5 submissions from di erent countries were received. The nal program included 3 full papers. All submissions were peer-reviewed by at least three internal Program Committee members on the basis of relevance for the workshop, novelty/originality, signi cance, technical quality and correctness, quality and clarity of presentation, quality of references and reproducibility, to ensure that only submissions of high quality were included in the workshop program. Authors were given 20 minutes to present their work, with 5 minutes for questions and answers. The presentations covered topics that span from the use of NLP patterns to explain and interpret sentiment in the nancial domain to the adoption of symbolic AI.
In addition to the paper presentations, the program included a 55-min keynote talk given by Prof. Erik Cambria from the Nanyang Technological University (NTU), Singapore. Prof. Cambria introduced the challenges that we are facing within the detection and explanations of sentiments such as the lack of transparency, traceability, and explainability on how the decisions are taken, thus limiting human-comprehensible solutions, and reducing the trust towards machine generated results.
Overall, the workshop was a successful event, as shown by the level of participation and the quality of the contributions during the presentations and the engagement of participants in the discussions. We believe that this workshop 1 https://danilo-dessi.github.io/xsentiment/ 2 we did not publish the proceedings of the fth edition of the workshop. helped to strengthen the community working on sentiment analysis and emotion detection, highlighting the current challenges, in particular regarding explainability, promoting discussions on ideas and solutions for these challenges, and also favouring the creation of networks of researchers for future initiatives related to these topics. There are already plans to organize the seventh edition of the workshop. The organizers would like to sincerely thank the main conference organizers, the keynote speaker, the paper authors, the programme committee, and the attendees for their valuable contribution to make this workshop a successful event.