File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Comparing a BERT Classifier and a GPT classifier for Detecting Connective Language Across Multiple Social Media
| Title | Comparing a BERT Classifier and a GPT classifier for Detecting Connective Language Across Multiple Social Media |
|---|---|
| Authors | |
| Issue Date | 1-Nov-2024 |
| Abstract | This study presents an approach for detecting connective language—defined as language that facilitates engagement, understanding, and conversation—from social media discussions. We developed and evaluated two types of classifiers: BERT and GPT-3.5 turbo. Our results demonstrate that the BERT classifier significantly outperforms GPT-3.5 turbo in detecting connective language. Furthermore, our analysis confirms that connective language is distinct from related concepts measuring discourse qualities, such as politeness and toxicity. We also explore the potential of BERT-based classifiers for platform-agnostic tools. This research advances our understanding of the linguistic dimensions of online communication and proposes practical tools for detecting connective language across diverse digital environments. |
| Persistent Identifier | http://hdl.handle.net/10722/351745 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Lukito, Josephine | - |
| dc.contributor.author | Chen, Bin | - |
| dc.contributor.author | Masullo, Gina M | - |
| dc.contributor.author | Stroud, Natalie Jomini | - |
| dc.date.accessioned | 2024-11-25T00:35:19Z | - |
| dc.date.available | 2024-11-25T00:35:19Z | - |
| dc.date.issued | 2024-11-01 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/351745 | - |
| dc.description.abstract | <p>This study presents an approach for detecting connective language—defined as language that facilitates engagement, understanding, and conversation—from social media discussions. We developed and evaluated two types of classifiers: BERT and GPT-3.5 turbo. Our results demonstrate that the BERT classifier significantly outperforms GPT-3.5 turbo in detecting connective language. Furthermore, our analysis confirms that connective language is distinct from related concepts measuring discourse qualities, such as politeness and toxicity. We also explore the potential of BERT-based classifiers for platform-agnostic tools. This research advances our understanding of the linguistic dimensions of online communication and proposes practical tools for detecting connective language across diverse digital environments.<br></p> | - |
| dc.language | eng | - |
| dc.relation.ispartof | EMNLP 2024 (12/11/2024-16/11/2024, Miami) | - |
| dc.title | Comparing a BERT Classifier and a GPT classifier for Detecting Connective Language Across Multiple Social Media | - |
| dc.type | Conference_Paper | - |
| dc.identifier.spage | 19140 | - |
| dc.identifier.epage | 19153 | - |