Enhancing Online Learning Experiences through Collaborative Thread Recommendation in Massive Open Online Courses (MOOCs)
Fuente:
Zenodo
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Recurso digital |
| Pubblicazione: |
Zenodo
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901191285276672 |
|---|---|
| author | Dr. Leila Alizadeh Dr. Rohan Desai |
| author_facet | Dr. Leila Alizadeh Dr. Rohan Desai |
| contents | <p>—Recommender Systems have been developed to provide contents and services compatible to users based on their behaviors and interests. Due to information overload in online discussion forums and users diverse interests, recommending relative topics and threads is considered to be helpful for improving the ease of forum usage. In order to lead learners to find relevant information in educational forums, recommendations are even more needed. We present a hybrid thread recommender system for MOOC forums by applying social network analysis and association rule mining techniques. Initial results indicate that the proposed recommender system performs comparatively well with regard to limited available data from users' previous posts in the forum</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19327128 |
| institution | Zenodo |
| language | |
| publishDate | 2023 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Enhancing Online Learning Experiences through Collaborative Thread Recommendation in Massive Open Online Courses (MOOCs) Dr. Leila Alizadeh Dr. Rohan Desai Association rule mining hybrid recommender system massive open online courses MOOCs social network analysis. <p>—Recommender Systems have been developed to provide contents and services compatible to users based on their behaviors and interests. Due to information overload in online discussion forums and users diverse interests, recommending relative topics and threads is considered to be helpful for improving the ease of forum usage. In order to lead learners to find relevant information in educational forums, recommendations are even more needed. We present a hybrid thread recommender system for MOOC forums by applying social network analysis and association rule mining techniques. Initial results indicate that the proposed recommender system performs comparatively well with regard to limited available data from users' previous posts in the forum</p> |
| title | Enhancing Online Learning Experiences through Collaborative Thread Recommendation in Massive Open Online Courses (MOOCs) |
| topic | Association rule mining hybrid recommender system massive open online courses MOOCs social network analysis. |
| url | https://doi.org/10.5281/zenodo.19327128 |