No abstract

Welcome to EVALITA 2020! EVALITA is the evaluation campaign of Natural Language Processing and Speech Tools for Italian. EVALITA is an initiative of the Italian Association for Computational Linguistics (AILC, http://www.ai-lc.it) and it is endorsed by the Italian Association for Artificial Intelligence (AIxIA, http://www.aixia.it) and the Italian Association for Speech Sciences (AISV, http://www.aisv.it).This volume includes the reports of both task organisers and participants to all of the EVALITA 2020 challenges. In the 2020 edition, we coordinated the organization of 14 different tasks belonging to five research areas, being: (i) Affect, Hate, and Stance, (ii) Creativity and Style, (iii) New Challenges in Long-standing Tasks, (iv) Semantics and Multimodality, Time and Diachrony.The volume is opened by an overview to the EVALITA 2020 campaign, in which we describe the tasks, provide statistics on the participants and task organizers as well as our supporting sponsors. The abstract of the keynote speech made by Preslav Nakov titled "Flattening the Curve of the COVID-19 Infodemic: These Evaluation Campaigns Can Help!" is also included in this collection.Due to the 2020 COVID-19 pandemic, the traditional workshop was held online, where several members of the Italian NLP Community presented the results of their research. Despite the circumstances, the workshop represented an occasion for all participants from both academic institutions and private companies to disseminate their work and results and to share ideas through online sessions dedicated to each task and a general discussion during the plenary event.We carried on with the tradition of the "Best system across tasks" award. As in 2018, it represented an incentive for students, IT developers and researchers to push the boundaries of the state of the art by facing tasks in new ways, even if not winning.

Social media platforms provide a goldmine for mining public opinion on issues of wide societal interest. Opinion mining is a problem that can be operationalised by capturing and aggregating the stance of individual social media posts as supporting, opposing or being neutral towards the issue at hand. While most prior work in stance detection has investigated datasets with limited time coverage, interest in investigating longitudinal datasets has recently increased. Evolving dynamics in linguistic and behavioural patterns observed in new data require in turn adapting stance detection systems to deal with the changes. In this survey paper, we investigate the intersection between computational linguistics and the temporal evolution of human communication in digital media. We perform a critical review in emerging research considering dynamics, exploring different semantic and pragmatic factors that impact linguistic data in general, and stance particularly. We further discuss current directions in capturing stance dynamics in social media. We organise the challenges of dealing with stance dynamics, identify open challenges and discuss future directions in three key dimensions: utterance, context and influence.

Given the rapidly evolving nature of social media and people's views, word usage changes over time. Consequently, the performance of a classifier trained on old textual data can drop dramatically when tested on newer data. While research in stance classification has advanced in recent years, no effort has been invested in making these classifiers have persistent performance over time.To study this phenomenon we introduce two novel large-scale, longitudinal stance datasets. We then evaluate the performance persistence of stance classifiers over time and demonstrate how it decays as the temporal gap between training and testing data increases. We propose a novel approach to mitigate this performance drop, which is based on temporal adaptation of the word embeddings used for training the stance classifier. This enables us to make use of readily available unlabelled data from the current time period instead of expensive annotation efforts. We propose and compare several approaches to embedding adaptation and find that the Incremental Temporal Alignment (ITA) model leads to the best results in reducing performance drop over time. CCS CONCEPTS• Computing methodologies → Natural language processing; Semi-supervised learning; Neural networks.

No abstract