Naslov
Are You Human? Detecting Bots on Twitter Using BERT

Autori
Dukić, David ; Keča, Dominik ; Stipić, Dominik

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA) / - : Institute of Electrical and Electronics Engineers (IEEE), 2020, 631-636

Skup
IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA 2020)

Mjesto i datum
Sydney, Australija, 06.10.2020. - 09.10.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
BERT model ; bot detection ; emoji2vec ; gender prediction ; latent Dirichlet allocation ; shallow vs. deep learning ; t-SNE

Sažetak
Dissemination of fake news on Twitter is a rapidly growing problem, mostly due to the increasing number of bots. Hence, automatic bot detection is becoming an important area of research. In this work, we present the BERT- based bot detection model along with exploratory data analysis of tweets written by bots and humans. We statistically prove that including additional features alongside contextualized embeddings boosts model performance. Furthermore, we develop a gender prediction model using derived features and compare the difficulties of the two tasks. Finally, we demonstrate how Logistic Regression outperforms Deep Neural Network on both tasks.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA