A5016281730- Multi-Agent Systems and Negotiation
- Semantic Web and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Logic, Reasoning, and Knowledge
- Access Control and Trust
- Hate Speech and Cyberbullying Detection
- Sentiment Analysis and Opinion Mining
- Artificial Intelligence in Law
- Service-Oriented Architecture and Web Services
- Software Engineering Research
- Business Process Modeling and Analysis
- Advanced Text Analysis Techniques
- Digital Rights Management and Security
- Biomedical Text Mining and Ontologies
- Misinformation and Its Impacts
- Scientific Computing and Data Management
- Data Quality and Management
- Auction Theory and Applications
- Game Theory and Applications
- Social Media and Politics
- Advanced Software Engineering Methodologies
- FinTech, Crowdfunding, Digital Finance
- Advanced Database Systems and Queries
- Privacy, Security, and Data Protection
Institut national de recherche en informatique et en automatique
2016-2025
Institut de Biologie Valrose
2023-2025
Centre National de la Recherche Scientifique
2016-2025
Université Côte d'Azur
2014-2025
Laboratoire d'Informatique, Signaux et Systèmes de Sophia Antipolis
2015-2025
Observatoire de la Côte d’Azur
2019-2023
Infection et inflammation
2020-2022
Fondazione Bruno Kessler
2020
Research Centre Inria Sophia Antipolis - Méditerranée
2012-2015
University of Turin
2008-2011
The increasing popularity of social media platforms such as Twitter and Facebook has led to a rise in the presence hate aggressive speech on these platforms. Despite number approaches recently proposed Natural Language Processing research area for detecting forms abusive language, issue identifying at scale is still an unsolved problem. In this article, we propose robust neural architecture that shown perform satisfactory way across different languages; namely, English, Italian, German. We...
Argument mining is the research area aiming at extracting natural language arguments and their relations from text, with final goal of providing machine-processable structured data for computational models argument. This topic has started to attract attention a small community researchers around 2014, it nowadays counted as one most promising areas in Artificial Intelligence terms growing community, funded projects, involvement companies. In this paper, we present argument tasks, discuss...
The field of computational models argument is emerging as an important aspect artificial intelligence research. reason for this based on the recognition that if we are to develop robust intelligent systems, then it imperative they can handle incomplete and inconsistent information in a way somehow emulates humans tackle such complex task. And one key ways do use argumentation either internally, by evaluating arguments counterarguments, or externally, instance entering into discussion debate...
With the growing use of Social Web, an increasing number applications for exchanging opinions with other people are becoming available online.These widely adopted consequence that about debated issues increases.In order to cut in on a debate, participants need first evaluate users detect whether they favour or against issue.Bipolar argumentation proposes algorithms and semantics set accepted arguments, given support attack relations among them.Two main problems arise.First, automated...
Social media collect and spread on the Web personal opinions, facts, fake news all kind of information users may be interested in. Applying argument mining methods to such heterogeneous data sources is a challenging open research issue, in particular considering peculiarities language used write textual messages social media. In addition, new issues emerge when dealing with arguments posted platforms, as need make distinction between opinions actual detect source disseminating about facts...
Ethics by Design concerns the methods, algorithms and tools needed to endow autonomous agents with capability reason about ethical aspects of their decisions, formalisms guarantee that an agent's behavior remains within given moral bounds. In this context some questions arise: How what extent can understand social reality in which they operate, other intelligences (AI, animals humans) co-exist? What are emerging new forms society, how do we ensure human dimension is upheld interactions...
Abstract The first issue of Artificial Intelligence and Law journal was published in 1992. This paper offers some commentaries on papers drawn from the Journal’s third decade. They indicate a major shift within Intelligence, both generally AI Law: away symbolic techniques to those based Machine Learning approaches, especially Natural Language texts rather than feature sets. Eight are discussed: two concern management use documents available World Wide Web, six apply machine learning variety...
The research carried out so far in detecting abusive content social media has primarily focused on overt forms of hate speech. While explicit speech (HS) is more easily identifiable by recognizing hateful words, messages containing linguistically subtle and implicit HS (as circumlocution, metaphors sarcasm) constitute a real challenge for automatic systems. the sneaky tricky nature might be perceived as less hurtful with respect to same expressed clearly, such abuse at least harmful abuse....
Research on language technology for the development of medical applications is currently a hot topic in Natural Language Understanding and Generation. Thus, number large models (LLMs) have recently been adapted to domain, so that they can be used as tool mediating human-AI interaction. While these LLMs display competitive performance automated texts benchmarks, pre-trained evaluated with focus single (English mostly). This particularly true text-to-text models, which typically require...
We review the First International Competition on Computational Models of Argumentation (ICCMA'15). The competition evaluated submitted solvers' performance four different computational tasks related to solving abstract argumentation frameworks. Each task solvers in ways that pushed edge existing by introducing new challenges. Despite being first this area, high number competitors entered, and differences results, suggest will help shape landscape ongoing developments theory solvers.