TY - GEN

T1 - Geolocation Detection Approaches for User Discussion Analysis in Twitter

AU - Blekanov, Ivan

AU - Maksimov, Alexey

AU - Nepiyushchikh, Dmitry

AU - Bodrunova, Svetlana S.

N1 - Conference code: 24

PY - 2022

Y1 - 2022

N2 - In this research, the authors consider methods for identifying geodata of users of social networks within user discussions. The knowledge of user geolocation data makes it possible to analyze the spread of discussion among users of different countries. Authors do not try to determine the exact geolocation, but rather the country where the users are located. The problem of getting country-level user location data lies in the fact that a high percentage of users do not state their location correctly, either mentioning it in humorous ways or even not stating it at all. There are various methods of obtaining data about the location of users. Among them, there are text-based methods, methods based on the analysis of the context, and methods based on the topology of the user graph. In this paper, we make a special emphasis on a method that allows to reveal geodata of users who specified their geodata incorrectly or did not specify it at all. In order to test our method, we use Twitter datasets. We propose several approaches to resolve the issues stated above. The paper highlights three approaches: the naïve approach, the naïve approach using natural language processing (NLP), and the graph approach, which is glossary-based and determines the number of outgoing connections. We have introduced two measures in order to evaluate the proposed approaches. Recall-GEO and Precision-GEO that are described throughout the paper. The accuracy of UserGraph method is finally evaluated using the metrics above.

AB - In this research, the authors consider methods for identifying geodata of users of social networks within user discussions. The knowledge of user geolocation data makes it possible to analyze the spread of discussion among users of different countries. Authors do not try to determine the exact geolocation, but rather the country where the users are located. The problem of getting country-level user location data lies in the fact that a high percentage of users do not state their location correctly, either mentioning it in humorous ways or even not stating it at all. There are various methods of obtaining data about the location of users. Among them, there are text-based methods, methods based on the analysis of the context, and methods based on the topology of the user graph. In this paper, we make a special emphasis on a method that allows to reveal geodata of users who specified their geodata incorrectly or did not specify it at all. In order to test our method, we use Twitter datasets. We propose several approaches to resolve the issues stated above. The paper highlights three approaches: the naïve approach, the naïve approach using natural language processing (NLP), and the graph approach, which is glossary-based and determines the number of outgoing connections. We have introduced two measures in order to evaluate the proposed approaches. Recall-GEO and Precision-GEO that are described throughout the paper. The accuracy of UserGraph method is finally evaluated using the metrics above.

KW - Geolocation detection

KW - Name entity recognition model

KW - Open street map service

KW - Social network analysis

KW - Twitter users discussion

KW - User graph analysis

UR - https://www.mendeley.com/catalogue/3716d7c2-d1b3-3483-8225-166b2c98d022/

U2 - 10.1007/978-3-031-22131-6_2

DO - 10.1007/978-3-031-22131-6_2

M3 - Conference contribution

SN - 9783031221309

T3 - Lecture Notes in Computer Science

SP - 16

EP - 29

BT - HCI International 2022 - Late Breaking Papers. Interaction in New Media, Learning and Games

PB - Springer Nature

Y2 - 26 June 2022 through 1 July 2022

ER -