arXiv subjects

Jose Alemany

Publications and source records attributed to Jose Alemany.

2 recordsLinked to original sources

arXiv2022

Toward the Prevention of Privacy Threats: How Can We Persuade Our Social Network Platform Users?

Complex decision-making problems such as the privacy policy selection when sharing content in online social networks can significantly benefit from artificial intelligence systems. With the use of Computational Argumentation, it is possible to persuade human users to modify their initial decisions to avoid potential privacy threats and violations. In this paper, we present a study performed over 186 teenage users aimed at analysing their behaviour when we try to persuade them to modify the publication of sensitive content in Online Social Networks (OSN) with different arguments. The results of the study revealed that the personality traits and the social interaction data (e.g., number of comments, friends, and likes) of our participants were significantly correlated with the persuasive power of the arguments. Therefore, these sets of features can be used to model OSN users, and to estimate the persuasive power of different arguments when used in human-computer interactions. The findings presented in this paper are helpful for personalising decision support systems aimed at educating and preventing privacy violations in OSNs using arguments.

cs.SI↗

arXiv2021

Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluation

Argument Mining is defined as the task of automatically identifying and extracting argumentative components (e.g., premises, claims, etc.) and detecting the existing relations among them (i.e., support, attack, rephrase, no relation). One of the main issues when approaching this problem is the lack of data, and the size of the publicly available corpora. In this work, we use the recently annotated US2016 debate corpus. US2016 is the largest existing argument annotated corpus, which allows exploring the benefits of the most recent advances in Natural Language Processing in a complex domain like Argument (relation) Mining. We present an exhaustive analysis of the behavior of transformer-based models (i.e., BERT, XLNET, RoBERTa, DistilBERT and ALBERT) when predicting argument relations. Finally, we evaluate the models in five different domains, with the objective of finding the less domain dependent model. We obtain a macro F1-score of 0.70 with the US2016 evaluation corpus, and a macro F1-score of 0.61 with the Moral Maze cross-domain corpus.

cs.CL↗