How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities
Fuente:
ERIC Institute of Education Sciences
Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso educativo Open Access |
| Language: | en |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1867181228890783744 |
|---|---|
| author | Katie Lai |
| author_facet | Katie Lai Katie Lai |
| collection | Education Resources Information Center |
| contents | How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities Katie Lai Artificial Intelligence Technology Uses in Education Library Services Reference Services Computer Mediated Communication Questioning Techniques Responses Natural Language Processing Information Dissemination Accuracy Usability User Needs (Information) User Satisfaction (Information) Difficulty Level To explore whether artificial intelligence can be used to enhance library services, this study used ChatGPT to answer reference questions. An assessment rubric was used to evaluate how well ChatGPT handled different question types and difficulty levels. Overall ChatGPT's performance was fair, but it did poorly in information accuracy. It scored the highest when handling facilities and equipment-related questions but the lowest when dealing with e-resources access problems. ChatGPT was weak in answering advanced research questions, complex inquiries, and known item searches relating to a specific local environment, but it could be adopted to enhance library communication with users. |
| format | Recurso educativo Open Access |
| id | eric_EJ1408775 |
| institution | ERIC Institute of Education Sciences |
| language | en |
| publishDate | 2023 |
| record_format | eric |
| spellingShingle | How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities Katie Lai Artificial Intelligence Technology Uses in Education Library Services Reference Services Computer Mediated Communication Questioning Techniques Responses Natural Language Processing Information Dissemination Accuracy Usability User Needs (Information) User Satisfaction (Information) Difficulty Level How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities Katie Lai Artificial Intelligence Technology Uses in Education Library Services Reference Services Computer Mediated Communication Questioning Techniques Responses Natural Language Processing Information Dissemination Accuracy Usability User Needs (Information) User Satisfaction (Information) Difficulty Level To explore whether artificial intelligence can be used to enhance library services, this study used ChatGPT to answer reference questions. An assessment rubric was used to evaluate how well ChatGPT handled different question types and difficulty levels. Overall ChatGPT's performance was fair, but it did poorly in information accuracy. It scored the highest when handling facilities and equipment-related questions but the lowest when dealing with e-resources access problems. ChatGPT was weak in answering advanced research questions, complex inquiries, and known item searches relating to a specific local environment, but it could be adopted to enhance library communication with users. |
| title | How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities |
| topic | Artificial Intelligence Technology Uses in Education Library Services Reference Services Computer Mediated Communication Questioning Techniques Responses Natural Language Processing Information Dissemination Accuracy Usability User Needs (Information) User Satisfaction (Information) Difficulty Level |
| url | https://eric.ed.gov/?id=EJ1408775 |