Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366850809> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4366850809 abstract "Harmful content is pervasive on social media, poisoning online communities and negatively impacting participation. A common approach to address this issue is to develop detection models that rely on human annotations. However, the tasks required to build such models expose annotators to harmful and offensive content and may require significant time and cost to complete. Generative AI models have the potential to understand and detect harmful content. To investigate this potential, we used ChatGPT and compared its performance with MTurker annotations for three frequently discussed concepts related to harmful content: Hateful, Offensive, and Toxic (HOT). We designed five prompts to interact with ChatGPT and conducted four experiments eliciting HOT classifications. Our results show that ChatGPT can achieve an accuracy of approximately 80% when compared to MTurker annotations. Specifically, the model displays a more consistent classification for non-HOT comments than HOT comments compared to human annotations. Our findings also suggest that ChatGPT classifications align with provided HOT definitions, but ChatGPT classifies hateful and offensive as subsets of toxic. Moreover, the choice of prompts used to interact with ChatGPT impacts its performance. Based on these in-sights, our study provides several meaningful implications for employing ChatGPT to detect HOT content, particularly regarding the reliability and consistency of its performance, its understand-ing and reasoning of the HOT concept, and the impact of prompts on its performance. Overall, our study provides guidance about the potential of using generative AI models to moderate large volumes of user-generated content on social media." @default.
- W4366850809 created "2023-04-25" @default.
- W4366850809 creator A5031522503 @default.
- W4366850809 creator A5033265331 @default.
- W4366850809 creator A5076021360 @default.
- W4366850809 creator A5077179813 @default.
- W4366850809 date "2023-04-20" @default.
- W4366850809 modified "2023-10-17" @default.
- W4366850809 title "HOT ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media" @default.
- W4366850809 doi "https://doi.org/10.48550/arxiv.2304.10619" @default.
- W4366850809 hasPublicationYear "2023" @default.
- W4366850809 type Work @default.
- W4366850809 citedByCount "1" @default.
- W4366850809 crossrefType "posted-content" @default.
- W4366850809 hasAuthorship W4366850809A5031522503 @default.
- W4366850809 hasAuthorship W4366850809A5033265331 @default.
- W4366850809 hasAuthorship W4366850809A5076021360 @default.
- W4366850809 hasAuthorship W4366850809A5077179813 @default.
- W4366850809 hasBestOaLocation W43668508091 @default.
- W4366850809 hasConcept C121332964 @default.
- W4366850809 hasConcept C127413603 @default.
- W4366850809 hasConcept C136764020 @default.
- W4366850809 hasConcept C154945302 @default.
- W4366850809 hasConcept C163258240 @default.
- W4366850809 hasConcept C167966045 @default.
- W4366850809 hasConcept C176856949 @default.
- W4366850809 hasConcept C2776436953 @default.
- W4366850809 hasConcept C39890363 @default.
- W4366850809 hasConcept C41008148 @default.
- W4366850809 hasConcept C42475967 @default.
- W4366850809 hasConcept C43214815 @default.
- W4366850809 hasConcept C518677369 @default.
- W4366850809 hasConcept C62520636 @default.
- W4366850809 hasConceptScore W4366850809C121332964 @default.
- W4366850809 hasConceptScore W4366850809C127413603 @default.
- W4366850809 hasConceptScore W4366850809C136764020 @default.
- W4366850809 hasConceptScore W4366850809C154945302 @default.
- W4366850809 hasConceptScore W4366850809C163258240 @default.
- W4366850809 hasConceptScore W4366850809C167966045 @default.
- W4366850809 hasConceptScore W4366850809C176856949 @default.
- W4366850809 hasConceptScore W4366850809C2776436953 @default.
- W4366850809 hasConceptScore W4366850809C39890363 @default.
- W4366850809 hasConceptScore W4366850809C41008148 @default.
- W4366850809 hasConceptScore W4366850809C42475967 @default.
- W4366850809 hasConceptScore W4366850809C43214815 @default.
- W4366850809 hasConceptScore W4366850809C518677369 @default.
- W4366850809 hasConceptScore W4366850809C62520636 @default.
- W4366850809 hasLocation W43668508091 @default.
- W4366850809 hasOpenAccess W4366850809 @default.
- W4366850809 hasPrimaryLocation W43668508091 @default.
- W4366850809 hasRelatedWork W2884815824 @default.
- W4366850809 hasRelatedWork W2910285800 @default.
- W4366850809 hasRelatedWork W2963062607 @default.
- W4366850809 hasRelatedWork W3003214776 @default.
- W4366850809 hasRelatedWork W3014074531 @default.
- W4366850809 hasRelatedWork W3017062960 @default.
- W4366850809 hasRelatedWork W3037703370 @default.
- W4366850809 hasRelatedWork W3113145805 @default.
- W4366850809 hasRelatedWork W3120345119 @default.
- W4366850809 hasRelatedWork W3215252950 @default.
- W4366850809 isParatext "false" @default.
- W4366850809 isRetracted "false" @default.
- W4366850809 workType "article" @default.