Compatibilità
Salva(0)
FBK's Camilla Casula participates as a speaker in this event organised by the HYBRIDS project in collaboration with IBERIFIER to talk about ‘Corpora Analysis in Social and Humanistic Domains’.
Program
Day 1: Tuesday, October 22
- 9:00 – 11:00
- Corpora Analysis in Social and Humanistic Domains
- In this seminar, we will discuss the importance of analyzing corpora before using them for research, including a deep-dive into Variationist, a tool that allows us to easily explore language corpora. The session will include examples of usage and hands-on exercises in which we will use this tool to gather information on datasets proposed by the attendants.
-
Speakers:
Day 2: Wednesday, October 23
- 9:00 – 11:00
- Detecting and Tackling Online Harms: From Rumours to Abuse
- Despite significant progress in developing NLP methods for tackling online harms such as misinformation and abusive language, there are still numerous shortcomings in existing models and datasets, not least when it comes to addressing more challenging circumstances. This talk will address challenges in data collection for rumour detection to generalisation in abusive language detection, looking at the challenges arising from the need to support diverse communities and users with different preferences.
-
Speakers:
- 14:30 – 16:30
- Exploring constructiveness and toxicity in online comments
- Abusive comments, toxic behaviour, harassment, misinformation and fake news—it seems like a bleak landscape online. Some of these problems can be solved with text classification techniques. If we can identify ‘nice’ and ‘nasty’ comments, then we can promote the former and filter out the latter. If we can reliably identify misinformation and fake news stories, then we can stop them before they spread online. My lab is actively working on these issues and I will discuss, in this talk, an ongoing research project which aims at identifying constructive comments on news stories. Using both ‘classic’ machine learning (Support Vector Machines with linguistic features) and deep learning methods, we have built a classifier to identify instances of constructive comments, defined as those that are related to the article, intend to create a civil dialogue and provide specific points supported by evidence. The classifier was built using a large annotated corpus of comments (12,000 comments) from the Canadian daily The Globe and Mail. Our results show that constructiveness can be identified reliably and that a mix of features characterize constructive comments, including length, specific points and the presence of personal stories. The goal of this project is to build a moderation platform to allow constructive comments to be featured more prominently, which will hopefully encourage more constructiveness in online spaces.
-
Speakers:
Day 3: Thursday, October 24
- 8:55 – 9:00
- Opening
-
Speakers:
Pablo Gamallo Otero (HYBRIDS Coordinator), Ramón Salaverría (IBERIFIER Coordinator)
- 9:00 – 9:15
- Analyzing the tactics and strategies adopted by individual and collective actors to propagate political opinions through media platforms.
- Presentation of HYBRIDS PhD Projects
-
Speakers:
- 9:15 – 9:30
- Discourse analysis in social networks
- Presentation of HYBRIDS PhD Projects.
-
Speakers:
- 9:30 – 9:45
- Multimodal and Multilingual Claim Retrieval for Automated Fact-Checking
- Presentation of HYBRIDS PhD Projects.
-
Speakers:
- 9:45 – 10:00
- Detecting Disinformation, Hyperpartisan News, and Online Harassment: A Hybrid Approach to Social Media Content Analysis
- Presentation of HYBRIDS PhD Projects.
-
Speakers:
- 10:00 – 11:00
- Joining forces against disinformation: the experience of Iberifier
- Promoted by the European Commission, the IBERIFIER observatory has been bringing together 25 public and private organizations from Spain and Portugal since 2021, including academic research institutions, news agencies, fact-checking groups, and strategic analysis entities. Through its work, reflected in various reports and outreach activities, the observatory has gained valuable insights into the nature, scope, and impact of disinformation across the Iberian region. This presentation will offer an overview of IBERIFIER’s structure, goals, and activities, highlighting potential opportunities for collaborative research and partnerships with other disinformation-focused projects.
-
Speakers:
- 11:00 – 11:30
- COFFEE BREAK
- 11:30 – 12:30
- Oppositional thinking analysis: Conspiracy theories vs critical thinking narratives
- The rise of social media has offered a fast and easy way for the propagation of disinformation. Several are the attempts of foreign information manipulation interference that our countries are exposed to. The European External Action Service and the European Digital Media Observatory are giving special importance to fight and analyse the disinformation narratives of this information warfare. Conspiracy theories are complex narratives that attempt to explain the ultimate causes of significant events as cover plots orchestrated by secret, powerful, and malicious groups. The majority of existing approaches do not distinguish between critical and conspiratorial thinking whereas this distinction has important implications for automatic content moderation: if models do not differentiate between critical and conspiratorial thinking, there is a high risk of pushing people toward conspiracy communities.
-
Speakers:
- 12:30 – 13:30
- Uninterested, tired, overwhelmed and avoidant: negative behaviors towards news and the consequences for journalism.
- The harsh contextual conditions threatening the survival of media and news brands have been widely acknowledged and covered by a wide range of approaches at a industrial, economic, social and cultural level. More recently, academics have been reckoning with an added threat, which is the rise of negative behaviors towards news. While sporadic negative behaviors towards journalism in audiences have been signaled before, the scale of phenomena such as the loss of interest, saturation and avoidance have reached concerning levels in recent years and for reasons experts tend to overlook: times have been tough for journalism and journalists, but they have been tough as well for audiences trying to make sense of pandemics, wars, inflationary crisis, etc. among other events. We look at the scale and size of such behaviors, trying to make sense of the ways in which audiences are taking control of their own news experience while also underlining the strategies in which journalism can be mobilised as a tool for problem solving and understanding, rather than a problem highlighter, adding emotional distress to already struggling audiences. This session aims to shed a light on how people, rather than being passive information receivers, are willing to take control of their own news experience in order to find solutions to everyday problems and, most importantly. to make sense of whats around them.
-
Speakers:
- 13:30 – 16:00
- LUNCH
- 16:00 – 18:00
- ROUND TABLE: AI, Disinformation, and Media
- The objective of this round table is to bring together journalists from various media outlets to share their experiences on the issue of disinformation. The discussion will focus on the role of AI and language models, exploring their contributions both in detecting disinformation and in its malicious spread. MODERATORS: Siddharth Bhargava (DC at FBK); Rafael Martins (DC at Newtral).
-
Speakers:
Alfonso Pato (elDiario.es), César Rodríguez (La Voz de Galicia), Guillermo Infantes (Newtral), Íñigo Caínzos (Cadena SER), Pablo Hernández Escayola (MALDITA.ES)
Day 4: Friday, October 25
- 11:15 – 13:00
- Verification journalists against disinformation
- The presentation will consist of an overview of the fact-checking work carried out by journalists specialized in verification. First, we will discuss the concept of disinformation that we work with at Newtral.es to determine what is verifiable and what is not, as well as the common patterns we observe in so-called “hoaxes.” I will also explain how disinformation exploits crisis contexts and present some specific examples in the following areas: hate speech, humanitarian and migratory crises, diplomatic relations, health, electoral processes, and wars. Lastly, I will mention the role of artificial intelligence in the field of disinformation.
-
Speakers:
- 13:00 – 14:30
- LUNCH
- 14:30 – 15:30
- Final discussion and farewell
About IBERIFIER:
IBERIFIER is a digital media observatory for Spain and Portugal, funded by the European Commission and connected to the European Digital Media Observatory (EDMO). Coordinated by the University of Navarra, IBERIFIER brings together twelve universities, five fact-checking organizations, news agencies, and six multidisciplinary research centers. The observatory focuses on combating disinformation and promoting media literacy across the Iberian Peninsula. You can find more information about Iberifier here.
About HYBRIDS:
The HYBRIDS project, funded by the Horizon Europe Marie Skłodowska-Curie Actions (HE MSCA) and co-funded by the UK Research and Innovation (UKRI) HE funding guarantee, addresses a broad spectrum of topics related to disinformation, abusive language, and public discourse. These include analyzing social media discourse, tracking the impact of political speech on public opinion, detecting hate speech, identifying toxic bots, and fact-checking claims, among others. Coordinated by CiTIUS at the University of Santiago de Compostela, the HYBRIDS consortium includes partner universities, research centers, non-profit organizations, and innovation companies from across Europe. You can find more information about HYBRIDS here.
FBK
