Papers by Traci Hong
Monitoring Hate Speech in Indonesia: An NLP-based Classification of Social Media Texts (2024.emnlp-demo)
Copied to clipboard
| Challenge: | a lack of mechanisms to track the spread and severity of hate speech complicates the formulation of effective solutions. |
| Approach: | They have developed a universally robust hate speech classifier tailored for a narrower subset of texts that target vulnerable groups that have historically been the targets of hate speech in Indonesia. |
| Outcome: | The proposed tool has persuaded the General Election Supervisory Body in Indonesia (BAWASLU) to collaborate with the Alliance of Independent Journalists (AJI) to monitor hate speech in vulnerable areas in the country known for hate speech dissemination or hate-related violence in the upcoming Indonesian regional elections. |
A Multi-Labeled Dataset for Indonesian Discourse: Examining Toxicity, Polarization, and Demographics Information (2025.findings-acl)
Copied to clipboard
Lucky Susanto, Musa Izzanardi Wijanarko, Prasetia Anugrah Pratama, Zilu Tang, Fariz Akyas, Traci Hong, Ika Karlina Idris, Alham Fikri Aji, Derry Tanti Wijaya
| Challenge: | Prior research has focused on toxicity and polarization as separate problems . extreme polarizing deepens divisions, often leading to hostility and fragmentation . |
| Approach: | They propose to use a multi-label Indonesian dataset annotated for toxicity, polarization, and annotator demographic information to study polarizing language and toxicity. |
| Outcome: | The proposed dataset shows that polarization cues improve toxicity classification and vice versa. |
COVID-19 Vaccine Misinformation in Middle Income Countries (2023.emnlp-main)
Copied to clipboard
| Challenge: | a multilingual dataset of COVID-19 vaccine misinformation is available from Brazil, Indonesia, and Nigeria. |
| Approach: | They propose to use a multilingual dataset of COVID-19 vaccine misinformation from Brazil, Indonesia, and Nigeria to assess their relevance to vaccines and the presence of misinformation. |
| Outcome: | The proposed models improve from 2.7 to 15.9 percentage points in macro F1-score compared to baseline models. |