Malicious Information Source Detection in Social Networks

This article presents the classification of fakes on grounds of the information source that underlies the occurrence of false information. The study was perfomed on the coronavirus fakes that spread in Russian Federation in March 2020 during the beginning of the coronavirus pandemic in our country. For the analysis, only those fakes were taken, which the Administrations of the Russian regions promptly denied in their official accounts on social networks. Based on this, only those fakes that caused the greatest public response were selected for analysis. In this article, the following types of fakes are distinguished: folklore, symmetric, interpretive, additional, and conspiracy. Folklore fakes in various variations reproduce the same motives and are associated with well-established ideas and stereotypes in the mass consciousness. Symmetrical fakes partially or completely transfer true facts from one territory (country, region) to another. They can also transfer information from one person (structure) to another (s). Interpretative fakes are associated with the incorrect interpretation of events, information disseminated, or decisions made by the authorities by individual individuals. Additional fakes for a short period of time continue the theme of previously thrown disinformation. Conspiracy fakes are associated with conspiracy theory, characterized by stuffing on a wide territory and a large audience This classification is not exhaustive and can be supplemented as new fakes appear and are studied. Also, within the framework of this article, recommendations are given on how to refute a particular fake, depending on its belonging to a particular type.

Download Full-text

Extraction and Analysis of Social Networks Data to Detect Traffic Accidents

Information ◽

10.3390/info13010026 ◽

2022 ◽

Vol 13 (1) ◽

pp. 26

Author(s):

Nestor Suat-Rojas ◽

Camilo Gutierrez-Osorio ◽

Cesar Pedraza

Keyword(s):

Social Networks ◽

Traffic Accident ◽

Traffic Accidents ◽

Low Cost ◽

Information Source ◽

Named Entity Recognition ◽

Industrial Area ◽

Entity Recognition ◽

Detection Methods ◽

Traffic Information

Traffic accident detection is an important strategy governments can use to implement policies intended to reduce accidents. They usually use techniques such as image processing, RFID devices, among others. Social network mining has emerged as a low-cost alternative. However, social networks come with several challenges such as informal language and misspellings. This paper proposes a method to extract traffic accident data from Twitter in Spanish. The method consists of four phases. The first phase establishes the data collection mechanisms. The second consists of vectorially representing the messages and classifying them as accidents or non-accidents. The third phase uses named entity recognition techniques to detect the location. In the fourth phase, locations pass through a geocoder that returns their geographic coordinates. This method was applied to Bogota city and the data on Twitter were compared with the official traffic information source; comparisons showed some influence of Twitter on the commercial and industrial area of the city. The results reveal how effective the information on accidents reported on Twitter can be. It should therefore be considered as a source of information that may complement existing detection methods.

Download Full-text