Details
| Original language | English |
|---|---|
| Title of host publication | FIRE 2021 Working Notes |
| Subtitle of host publication | Working Notes of FIRE 2021 - Forum for Information Retrieval Evaluation |
| Pages | 412-418 |
| Number of pages | 7 |
| Publication status | Published - Dec 2021 |
| Event | Working Notes of FIRE - 13th Forum for Information Retrieval Evaluation, FIRE-WN 2021 - Gandhinagar, India Duration: 13 Dec 2021 → 17 Dec 2021 |
Publication series
| Name | CEUR Workshop Proceedings |
|---|---|
| Publisher | CEUR Workshop Proceedings |
| Volume | 3159 |
| ISSN (Print) | 1613-0073 |
Abstract
The detection of offensive, hateful and profane language has become a critical challenge since many users in social networks are exposed to cyberbullying activities on a daily basis. In this paper, we present an analysis of combining different textual features for the detection of hateful or offensive posts on Twitter. We provide a detailed experimental evaluation to understand the impact of each building block in a neural network architecture. The proposed architecture is evaluated on the English Subtask 1A: Identifying Hate, offensive and profane content from the post datasets of HASOC-2021 dataset under the team name TIB-VA. We compared different variants of the contextual word embeddings combined with the character level embeddings and the encoding of collected hate terms.
Keywords
- abusive language detection, hate speech detection, offensive language detection, social media mining
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
FIRE 2021 Working Notes: Working Notes of FIRE 2021 - Forum for Information Retrieval Evaluation. 2021. p. 412-418 (CEUR Workshop Proceedings; Vol. 3159).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Combining Textual Features for the Detection of Hateful and Offensive Language
AU - Hakimov, Sherzod
AU - Ewerth, Ralph
PY - 2021/12
Y1 - 2021/12
N2 - The detection of offensive, hateful and profane language has become a critical challenge since many users in social networks are exposed to cyberbullying activities on a daily basis. In this paper, we present an analysis of combining different textual features for the detection of hateful or offensive posts on Twitter. We provide a detailed experimental evaluation to understand the impact of each building block in a neural network architecture. The proposed architecture is evaluated on the English Subtask 1A: Identifying Hate, offensive and profane content from the post datasets of HASOC-2021 dataset under the team name TIB-VA. We compared different variants of the contextual word embeddings combined with the character level embeddings and the encoding of collected hate terms.
AB - The detection of offensive, hateful and profane language has become a critical challenge since many users in social networks are exposed to cyberbullying activities on a daily basis. In this paper, we present an analysis of combining different textual features for the detection of hateful or offensive posts on Twitter. We provide a detailed experimental evaluation to understand the impact of each building block in a neural network architecture. The proposed architecture is evaluated on the English Subtask 1A: Identifying Hate, offensive and profane content from the post datasets of HASOC-2021 dataset under the team name TIB-VA. We compared different variants of the contextual word embeddings combined with the character level embeddings and the encoding of collected hate terms.
KW - abusive language detection
KW - hate speech detection
KW - offensive language detection
KW - social media mining
UR - http://www.scopus.com/inward/record.url?scp=85134272740&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2112.04803
DO - 10.48550/arXiv.2112.04803
M3 - Conference contribution
AN - SCOPUS:85134272740
T3 - CEUR Workshop Proceedings
SP - 412
EP - 418
BT - FIRE 2021 Working Notes
T2 - Working Notes of FIRE - 13th Forum for Information Retrieval Evaluation, FIRE-WN 2021
Y2 - 13 December 2021 through 17 December 2021
ER -