Call for Participation: EMit - Categorical Emotions Detection in Italian shared task at EVALITA 2023




Categorical Emotions Detection in Italian shared task at EVALITA 2023


Info: http://www.di.unito.it/~tutreeb/emit23/index.html 


EVALITA 2023, the 8th evaluation campaign of Natural Language Processing and Speech tools for Italian, 7-8 September 2023, Parma, Italy


Registration is required to obtain data and participate in the shared task.

Subscribe to the google group: emit_evalita2023@googlegroups.com 





The detection of emotions in texts has a long history in international evaluation campaigns (at SemEval in 2007, 2018 and 2019, or TASS 2020, EmoEvalEs 2021, EmotionX 2018 and 2019, and WASSA 2022 and 2023), but has never been addressed in EVALITA where the only shared task to deal with emotions was about emotional speech recognition systems (ERT 2014).


In this context, the EMit (Emotions in Italian) task aims at providing the first evaluation framework for categorical emotion detection in Italian texts (with a specific attention on the entertainment sector) and make new annotated data available to the community.


Task Description

EMit  is organized according to two subtasks, both designed as multilabel classification problems:

  1. SUBTASK A: Categorial Emotion Detection (mandatory). The main proposed subtask concerns the detection of emotions in social media messages about TV shows emitted by RAI (Radiotelevisione italiana, the national public broadcasting company of Italy) and other out-of-domain texts.
  2. SUBTASK B: Target Detection (optional). The second subtask is about the detection of the target addressed by the author of the message: the topic or the direction. In each text, it should be indicated whether this refers to what the broadcast is about (the topic) or whether it refers to something that is under control of the broadcast itself (the direction).


*Important Dates*


7th February 2023: training data available to participants

30th April 2023: registration closes 

2nd-19th May 2023: evaluation window and collection of participants’ results

30th May 2023: assessment returned to participants

14th June 2023: final reports from task participants due to task organizers

25th July 2023: camera ready version deadline

7th-8th September 2023: final workshop in Parma




Oscar Araque: Universidad Politécnica de Madrid, Madrid, Spain

Simona Frenda: Università degli Studi di Torino, Turin, Italy 

Debora Nozza: Università Bocconi, Milan, Italy

Viviana Patti: Università degli Studi di Torino, Turin, Italy 

Rachele Sprugnoli: Università di Parma, Parma, Italy

If you have any enquiries/comments, contact us via: emit_evalita2023@googlegroups.com

Special Issue Information


Dear Colleagues,

Recent advances in natural language processing (NLP) that involve machine learning and deep learning have certainly revolutionized the field. Still, there are specific tasks and domains where these new techniques have still not surpassed more classical approaches—for example, tasks that require deep linguistic knowledge such as natural language understanding, semantic reasoning, and question answering. Another common limitation is that of the scarcity of training datasets, a situation that arises when trying to apply recent approaches to new domains. To overcome these limitations, it is necessary to consider hybrid systems that exploit domain-oriented knowledge into learning models in a way that allows machines to grasp the intricacies of real-world applications, equipping them with deep understanding and general common sense.

While there are efforts to design hybrid models, several aspects need to be considered. such as interpretability, transparency, accountability, and efficiency. This Special Issue of Electronics addresses the direction of NLP efforts toward hybrid solutions, considering the mentioned characteristics and their effects on end users and society in general.

Topics of interest of this Special Issue include but are not limited to:

  • Information extraction;
  • Semantic reasoning;
  • Text and speech processing;
  • Relational semantics;
  • Discourse analysis;
  • Argument mining;
  • Text summarization;
  • Machine translation;
  • Natural language generation;
  • Natural language understanding;
  • Question answering;
  • Sentiment and emotion analysis;
  • Affect analysis;
  • Hate speech analysis;
  • Radicalization analysis;
  • Disinformation analysis;
  • Authorship attribution.

Dr. Oscar Araque
Dr. Lorenzo Gatti
Dr. Álvaro Carrera Barroso
Dr. Kyriaki Kalimeri
Guest Editors


Special Issue Information

Dear Colleagues,

Interest in social media has only increased with time. Social media today represent the main channel to communicate and to share personal information. Social media analysis usually combines content-based and network-based analysis. While content-based approaches analyze media using media analysis techniques, network-based approaches analyze static and dynamic network properties with the aim of detecting influencers for marketing purposes. Network-based analysis represents a fundamental process in order to understand the dynamics of these platforms. New techniques and technologies have been proposed in order to enrich the social media analytics field. In particular, decentralized approaches have been proposed in order to face privacy issues, and AI has been applied in order to improve analysis over large sets of data. The main goal of this Special Issue is to collect research contributions, applications, analyses, methodologies, or strategies that strengthen or face the knowledge of social media thanks to advanced analyses or new technologies, such as P2P networks or blockchain. We hope that this Special Issue will contribute to raising awareness about new proposals and the impact of new technologies on social media. Potential topics include, but are not limited to, the following: - Social media analysis;- Decentralized approaches for social media;- Blockchain social media: analysis and applications;- AI for social media;- Social media mining;- Privacy in social media;- Fake news and misinformation.

Dr. Barbara Guidi
Dr. Carlos A. Iglesias
Dr. Giulio Rossetti
Dr. Kevin Koidl
Guest Editors


More information at https://www.mdpi.com/journal/applsci/special_issues/analysis_social_media 

Call for Paper

The 1st International Electronic Conference on Applied Sciences will be held on 10–30 November 2020ASEC 2020 aims to promote and advance the exciting and rapidly changing field of applied sciences. All proceedings will be held online at https://sciforum.net/conference/ASEC2020.

Topics of interest include, but are not limited to:

ASEC 2020 is a virtual conference sponsored by Applied Sciences. Participation is free of charge for authors and attendees. Accepted papers will be gathered in the proceedings of the conference. Selected extended versions of the papers will be published in a Special Issue of Applied Sciences and undergo full peer review (ISSN 2076-3417; Impact Factor: 2.474 (2018)) with a 10% discount on the article processing charge. ASEC 2020 offers you the opportunity to participate in this international, scholarly conference without the concerns or expenditure of travel—all you need is your computer and access to the internet. We would like to invite you to attend this conference and present your latest work.

Abstracts (in English) should be submitted online by 28 October 2020 at https://sciforum.net/conference/ASEC2020. For accepted abstracts, the proceedings can be submitted by 31 October 2020. The conference will be held on 10–30 November 2020.

Paper Submission Guidelines

For information about the submission procedure and preparation of a full presentation, please refer to the "Instructions for Authors".

Time Schedule


  • Abstract Submission: 28 October 2020
  • Notification of Acceptance: 30 October 2020
  • Paper Submission Deadline: 31 October 2020
  • Conference Open: 10–30 November 2020

Special Issue "News Research in Social Networks and Social Media" - Journal Information

In recent years, the news industry has undergone a big transformation as a consequence of its online diffusion. According to a recent survey, social media has become an important source of news for adults around the world. Nevertheless, this survey also revealed that phenomena such as fake news have had a serious impact on the credibility of online news. Additionally, scientific and technical progress has enabled the increasing adoption of data-driven news generation. Lastly, online news provides a rich dataset for understanding the characteristics of news media channels, such as political leaning and tone, as well as news consumption and sharing dynamics.


This Special Issue aims to provide an overview of the application of intelligent techniques in the news domain. The key areas of this Special Issue include, but are not limited to:

  • Fake news detection (both explainable and multi-
  • modal);
  • News analytics and classification;
  • News similarity and clustering;
  • News provenance;
  • Automated news generation;
  • News event and topic evolution;
  • News framing research;
  • News personalization;
  • News emotion prediction and detection;
  • News sharing, diffusion, and consumption.


Journal Information Scopus 2.4, SJR Q3 https://www.scopus.com/sourceid/21100223111#tabs=0

More information: https://www.mdpi.com/journal/information/special_issues/news_research-socialmedia