Twitter account classification using account metadata: organization vs. individual

Date

2022-01-01

Author

Çetinkaya, Yusuf Mucahit
Gürlek, Mesut
Toroslu, İsmail Hakkı
Karagöz, Pınar

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

253
views

0
downloads

Organizations present their existence on social media to gain followers and reach out to the crowds. Social media-related tasks and applications, such as social media graph construction, sentiment analysis, and bot detection, are required to identify the entities’ account types. Some applications focus on personal accounts, whereas others only need nonpersonal accounts. This paper addresses the account classification problem using only minimum amount of data, which is the metadata of the account’s profile. The proposed approach classifies accounts either as organization or individual, in a language-independent manner, without collecting the accounts’ tweet content. The model uses a long short term memory (LSTM) network for processing the textual properties and a fully-connected neural network for processing the numerical features. We apply our solution to a collection of Twitter accounts, as it is one of the most widely used social networks. Our classifier, based solely on the account metadata, achieves an average of 97.4% accuracy under 7-fold cross-validation. The experiments show that the account metadata is a qualified resource for accurately estimating the account types.

URI

https://journals.tubitak.gov.tr/elektrik/vol30/iss4/16/
https://hdl.handle.net/11511/97498

Journal

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES

DOI

https://doi.org/10.55730/1300-0632.3856

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Twitter use by politicians during social uprisings an analysis of Gezi park protests in Turkey KARKIN, NACİ; Yavuz, Nilay; PARLAK, İSMET; İKİZ, ÖZLEM ÖZDEŞİM (2015-06-30) Social uprisings clearly show that social media tools, especially Twitter, help news spread more than the press does recently. In some cases Twitter substitutes traditional media if censorship is enlarged to such a level that the mainstream media channels prefer not to reflect the actual volume of the protests. Twitter is also utilized by politicians during such events to reinforce "us vs. them" division, and to gain support and legitimization for their own actions. Using critical discourse analysis, this p...
Context Based Semantic Relations in Tweets Özer, Özdikiş; Karagöz, Pınar; Oğuztüzün, Mehmet Halit Seyfullah (Springer, 2014-01-01) Twitter, a popular social networking platform, provides a medium for people to share information and opinions with their followers. In such a medium, a flash event finds an immediate response. However, one concept may be expressed in many different ways. Because of users’ different writing conventions, acronym usages, language differences, and spelling mistakes, there may be variations in the content of postings even if they are about the same event. Analyzing semantic relationships and detecting these vari...
SOCIAL MEDIA FOR HIGHER EDUCATION FROM STUDENTS' PERSPECTIVES Celik, Ilknur (2015-07-08) Social media has received a worldwide adoption over the last decade for various purposes from communication to exchange of ideas, marketing, networking, following news or celebrities, and even to utilization as a trigger for social movements. Hence, the potential use of this medium for education needs exploration. This study presents Turkish higher education students' current practices and perceptions towards social media, and its potential use for learning in higher education. An online survey was administ...
FACT EXTRACTION AND VERIFICATION PIPELINE FOR COVID-19 RELATED USER POSTS IN SOCIAL MEDIA Temiz, Orkun; Taşkaya Temizel, Tuğba; Department of Bioinformatics (2022-6-29) Social media has become a prevalent platform for consuming and sharing information online. The vast amounts of information, shared easily and rapidly by social media, have increased the demand for fact-checking. Misinformation threatens not only the reputation of individuals and organizations but also society. When the COVID-19 pandemic broke out, the concerns around misinformation, which threatens public health and society, have significantly increased. In this thesis, a new zero-shot fact extraction and v...
Usability in Local E-Government: Analysis of Turkish Metropolitan Municipality Facebook Pages YILDIZ, METE; Ocak, Nihan; Yildirim, Caglar; Çağıltay, Kürşat; Babaoglu, Cenay (2016-01-01) Social media use is on the rise throughout the world. Influenced by this trend, governments of all levels and sizes are establishing their social media (like Facebook) presence due to the communication and interaction capabilities that such a presence brings. This study examines and explains the social media presence of Turkish local governments from a usability perspective. Usability studies provide governments with important empirical data about the citizens'/users' view/perception of the efficiency, effe...

Citation Formats

Y. M. Çetinkaya, M. Gürlek, İ. H. Toroslu, and P. Karagöz, “Twitter account classification using account metadata: organization vs. individual,” TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, vol. 30, no. 4, pp. 1404–1418, 2022, Accessed: 00, 2022. [Online]. Available: https://journals.tubitak.gov.tr/elektrik/vol30/iss4/16/.