Description-based Post-hoc Explanation for Twitter List Recommendations
Twitter List recommender systems can generate highly accurate recommendations, but since they employ heterogeneous information of users and Lists and apply complex prediction models, they cannot provide easy understandable intrinsic explanations. To address this limitation, Twitter List descriptions...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ferdowsi University of Mashhad
2024-12-01
|
| Series: | Computer and Knowledge Engineering |
| Subjects: | |
| Online Access: | https://cke.um.ac.ir/article_45395_1c89aae7af5bb5910ceec68253f32739.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595470956888064 |
|---|---|
| author | Havva Alizadeh Noughabi Behshid Behkamal Mohsen Kahani |
| author_facet | Havva Alizadeh Noughabi Behshid Behkamal Mohsen Kahani |
| author_sort | Havva Alizadeh Noughabi |
| collection | DOAJ |
| description | Twitter List recommender systems can generate highly accurate recommendations, but since they employ heterogeneous information of users and Lists and apply complex prediction models, they cannot provide easy understandable intrinsic explanations. To address this limitation, Twitter List descriptions can play a critical role in providing post-hoc explanations that help users make informed decisions. In this paper, we propose an explanation model to provide relevant and informative explanations for recommended Lists by automatically generating descriptions for Twitter Lists. The model selects the most informative tweets from a List as its description to inform users more with the recommended List that positively contributes to the user experience. More specifically, the explanation model incorporates three categories of features: content relevance features, tweet-specific features, and publisher’s authority features that are used in a learning to rank model to rank the List’s tweets in terms of their informativeness. By conducting experiments on a Twitter dataset, we have shown that the proposed model provides useful explanations for the Lists that are recommended to users, while upholding parity in recommendation performance. |
| format | Article |
| id | doaj-art-66f3af40f2fe4b5a94f935c26bf6ff08 |
| institution | Kabale University |
| issn | 2538-5453 2717-4123 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Ferdowsi University of Mashhad |
| record_format | Article |
| series | Computer and Knowledge Engineering |
| spelling | doaj-art-66f3af40f2fe4b5a94f935c26bf6ff082025-01-19T04:04:23ZengFerdowsi University of MashhadComputer and Knowledge Engineering2538-54532717-41232024-12-0172435010.22067/cke.2024.85185.110745395Description-based Post-hoc Explanation for Twitter List RecommendationsHavva Alizadeh Noughabi0Behshid Behkamal1Mohsen Kahani2Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran.Twitter List recommender systems can generate highly accurate recommendations, but since they employ heterogeneous information of users and Lists and apply complex prediction models, they cannot provide easy understandable intrinsic explanations. To address this limitation, Twitter List descriptions can play a critical role in providing post-hoc explanations that help users make informed decisions. In this paper, we propose an explanation model to provide relevant and informative explanations for recommended Lists by automatically generating descriptions for Twitter Lists. The model selects the most informative tweets from a List as its description to inform users more with the recommended List that positively contributes to the user experience. More specifically, the explanation model incorporates three categories of features: content relevance features, tweet-specific features, and publisher’s authority features that are used in a learning to rank model to rank the List’s tweets in terms of their informativeness. By conducting experiments on a Twitter dataset, we have shown that the proposed model provides useful explanations for the Lists that are recommended to users, while upholding parity in recommendation performance.https://cke.um.ac.ir/article_45395_1c89aae7af5bb5910ceec68253f32739.pdfexplainable recommender systemspost-hoc explanationdescription generationtwitter lists |
| spellingShingle | Havva Alizadeh Noughabi Behshid Behkamal Mohsen Kahani Description-based Post-hoc Explanation for Twitter List Recommendations Computer and Knowledge Engineering explainable recommender systems post-hoc explanation description generation twitter lists |
| title | Description-based Post-hoc Explanation for Twitter List Recommendations |
| title_full | Description-based Post-hoc Explanation for Twitter List Recommendations |
| title_fullStr | Description-based Post-hoc Explanation for Twitter List Recommendations |
| title_full_unstemmed | Description-based Post-hoc Explanation for Twitter List Recommendations |
| title_short | Description-based Post-hoc Explanation for Twitter List Recommendations |
| title_sort | description based post hoc explanation for twitter list recommendations |
| topic | explainable recommender systems post-hoc explanation description generation twitter lists |
| url | https://cke.um.ac.ir/article_45395_1c89aae7af5bb5910ceec68253f32739.pdf |
| work_keys_str_mv | AT havvaalizadehnoughabi descriptionbasedposthocexplanationfortwitterlistrecommendations AT behshidbehkamal descriptionbasedposthocexplanationfortwitterlistrecommendations AT mohsenkahani descriptionbasedposthocexplanationfortwitterlistrecommendations |