Assessing topic-based users credibility in twitter.
Saved in:
| Title: | Assessing topic-based users credibility in twitter. |
|---|---|
| Authors: | Meddeb, Amna1 (AUTHOR) amna.meddeb@isitc.u-sousse.tn, Ben Romdhane, Lotfi1 (AUTHOR) |
| Source: | Multimedia Tools & Applications. Jul2024, Vol. 83 Issue 23, p63329-63351. 23p. |
| Subjects: | Online social networks, Microblogs, Natural language processing, Research personnel |
| Abstract: | Online Social Networks (OSN) have become an inevitable source of information. Every user in OSNs can share true or false information regardless of their knowledge. False information can cause damage to people, companies, and even societies. Thus investigating the correctness of information on OSN is crucial. Several researchers worked on assessing users' credibility because if a person is considered credible, so will the information he/she shares. In this paper, we introduce a novel approach that assesses topic-based credibility of users where a user's credibility varies with topics. First, we assess the topic-based credibility of a user's tweets and then calculate users' expertise in a range of topics. Afterward, we introduce new graph-based measures that consider semantic and structural aspects to assess the influence of experts versus the influence of rumor spreaders on the user's credibility. Finally, in the experimental section, the impact of working on a topic basis on tweets' credibility is investigated showing that topic-based results are better than topic-independent tweets' credibility results. In addition, the topic-based credibility of OSN users and how it is influenced by experts and rumor spreaders is analyzed revealing that experts have a positive and strong impact compared to rumor spreaders' negative impact on users' credibility results. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Online Social Networks (OSN) have become an inevitable source of information. Every user in OSNs can share true or false information regardless of their knowledge. False information can cause damage to people, companies, and even societies. Thus investigating the correctness of information on OSN is crucial. Several researchers worked on assessing users' credibility because if a person is considered credible, so will the information he/she shares. In this paper, we introduce a novel approach that assesses topic-based credibility of users where a user's credibility varies with topics. First, we assess the topic-based credibility of a user's tweets and then calculate users' expertise in a range of topics. Afterward, we introduce new graph-based measures that consider semantic and structural aspects to assess the influence of experts versus the influence of rumor spreaders on the user's credibility. Finally, in the experimental section, the impact of working on a topic basis on tweets' credibility is investigated showing that topic-based results are better than topic-independent tweets' credibility results. In addition, the topic-based credibility of OSN users and how it is influenced by experts and rumor spreaders is analyzed revealing that experts have a positive and strong impact compared to rumor spreaders' negative impact on users' credibility results. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-023-18093-9 |
