In the past decade, social media have become increasingly popular for information consumption, due to its easy access, fast dissemination, and low-cost production. However, compared to this explosion of information content, social media presents two major problems. The first concerns the potential propagation of misinformation, often in the form of fake news, which can have significant negative societal effects. The second concerns the extreme difficulty that users may have in finding information of interest in a context characterized by information overload. In this paper, both of these problems are considered and analyzed together. In fact, the main goal of this work is to study the problem of generating automatic summaries of texts (around specific topics of interest) that are at the same time credible. This task has been very little studied in the literature, so this contribution can be considered one of the first works about credible text summarization.
Talarico, F., Viviani, M. (2021). Credible Text Summarization in Social Media. In WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Melbourne VIC Australia, December 14-17, 2021 (pp.603-610). New York : Association for Computing Machinery [10.1145/3486622.3493978].
Credible Text Summarization in Social Media
Viviani, M
2021
Abstract
In the past decade, social media have become increasingly popular for information consumption, due to its easy access, fast dissemination, and low-cost production. However, compared to this explosion of information content, social media presents two major problems. The first concerns the potential propagation of misinformation, often in the form of fake news, which can have significant negative societal effects. The second concerns the extreme difficulty that users may have in finding information of interest in a context characterized by information overload. In this paper, both of these problems are considered and analyzed together. In fact, the main goal of this work is to study the problem of generating automatic summaries of texts (around specific topics of interest) that are at the same time credible. This task has been very little studied in the literature, so this contribution can be considered one of the first works about credible text summarization.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.