Saved in:
| Main Authors: | , |
|---|---|
| Format: | Recurso educativo Open Access |
| Language: | en |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://eric.ed.gov/?id=EJ1306530 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1867181343024087040 |
|---|---|
| author | Walker, Jeremy Coleman, Jason |
| author_facet | Walker, Jeremy Coleman, Jason Walker, Jeremy Coleman, Jason |
| collection | Education Resources Information Center |
| contents | Using Machine Learning to Predict Chat Difficulty Walker, Jeremy Coleman, Jason Artificial Intelligence Natural Language Processing Prediction Library Services Reference Services Computer Mediated Communication Academic Libraries Transcripts (Written Records) Models This study aims to evaluate the effectiveness and potential utility of using machine learning and natural language processing techniques to develop models that can reliably predict the relative difficulty of incoming chat reference questions. Using a relatively large sample size of chat transcripts (N = 15,690), an empirical experimental design was used to test and evaluate 640 unique models. Results showed the predictive power of observed modeling processes to be highly statistically significant. These findings have implications for how library service managers may seek to develop and refine reference services using advanced analytical methods. |
| format | Recurso educativo Open Access |
| id | eric_EJ1306530 |
| institution | ERIC Institute of Education Sciences |
| language | en |
| publishDate | 2021 |
| record_format | eric |
| spellingShingle | Using Machine Learning to Predict Chat Difficulty Walker, Jeremy Coleman, Jason Artificial Intelligence Natural Language Processing Prediction Library Services Reference Services Computer Mediated Communication Academic Libraries Transcripts (Written Records) Models Using Machine Learning to Predict Chat Difficulty Walker, Jeremy Coleman, Jason Artificial Intelligence Natural Language Processing Prediction Library Services Reference Services Computer Mediated Communication Academic Libraries Transcripts (Written Records) Models This study aims to evaluate the effectiveness and potential utility of using machine learning and natural language processing techniques to develop models that can reliably predict the relative difficulty of incoming chat reference questions. Using a relatively large sample size of chat transcripts (N = 15,690), an empirical experimental design was used to test and evaluate 640 unique models. Results showed the predictive power of observed modeling processes to be highly statistically significant. These findings have implications for how library service managers may seek to develop and refine reference services using advanced analytical methods. |
| title | Using Machine Learning to Predict Chat Difficulty |
| topic | Artificial Intelligence Natural Language Processing Prediction Library Services Reference Services Computer Mediated Communication Academic Libraries Transcripts (Written Records) Models |
| url | https://eric.ed.gov/?id=EJ1306530 |