An effective explainable food recommendation using deep image clustering and community detection
In food diet communication domain, images convey important information to capture users' attention beyond the traditional ingredient content, making it crucial to influence user-decision about the relevancy of a given diet. By using a deep learning-based image clustering method, this paper prop...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Intelligent Systems with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305322000941 |
| _version_ | 1798016079699640320 |
|---|---|
| author | Mehrdad Rostami Usman Muhammad Saman Forouzandeh Kamal Berahmand Vahid Farrahi Mourad Oussalah |
| author_facet | Mehrdad Rostami Usman Muhammad Saman Forouzandeh Kamal Berahmand Vahid Farrahi Mourad Oussalah |
| author_sort | Mehrdad Rostami |
| collection | DOAJ |
| description | In food diet communication domain, images convey important information to capture users' attention beyond the traditional ingredient content, making it crucial to influence user-decision about the relevancy of a given diet. By using a deep learning-based image clustering method, this paper proposes an Explainable Food Recommendation system that uses the visual content of food to justify their recommendations. n the recommendation system. Especially, a new similarity score based on a tendency measure that quantifies the extent to which user community prefers a given food category is introduced and incorporated in the recommendation. Finally, a rule-based explainability is introduced to enhance transparency and interpretability of the recommendation outcome. Our experiments on a crawled dataset showed that the proposed method enhances recommendation quality in terms of precision, recall, F1, and Normalized Discounted Cumulative Gain (NDCG) by 7.35%, 6.70%, 7.32% and 14.38%, respectively, when compared to other existing methodologies for food recommendation. Besides ablation study is performed to demonstrate the technical soundness of the various components of our recommendation system. |
| first_indexed | 2024-04-11T15:45:05Z |
| format | Article |
| id | doaj.art-b7400217d63d49c1b8609816c941ba48 |
| institution | Directory Open Access Journal |
| issn | 2667-3053 |
| language | English |
| last_indexed | 2024-04-11T15:45:05Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Intelligent Systems with Applications |
| spelling | doaj.art-b7400217d63d49c1b8609816c941ba482022-12-22T04:15:38ZengElsevierIntelligent Systems with Applications2667-30532022-11-0116200157An effective explainable food recommendation using deep image clustering and community detectionMehrdad Rostami0Usman Muhammad1Saman Forouzandeh2Kamal Berahmand3Vahid Farrahi4Mourad Oussalah5Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland; Corresponding author.Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, FinlandSchool of Mathematics and Statistics, University of New South Wales, Sydney, NSW, AustraliaSchool of Computer Sciences, Science and Engineering Faculty, Queensland University of Technology (QUT), AustraliaCenter for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland; Research Unit of Medical Imaging, Physics and Technology, University of Oulu, FinlandCenter for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland; Research Unit of Medical Imaging, Physics and Technology, University of Oulu, FinlandIn food diet communication domain, images convey important information to capture users' attention beyond the traditional ingredient content, making it crucial to influence user-decision about the relevancy of a given diet. By using a deep learning-based image clustering method, this paper proposes an Explainable Food Recommendation system that uses the visual content of food to justify their recommendations. n the recommendation system. Especially, a new similarity score based on a tendency measure that quantifies the extent to which user community prefers a given food category is introduced and incorporated in the recommendation. Finally, a rule-based explainability is introduced to enhance transparency and interpretability of the recommendation outcome. Our experiments on a crawled dataset showed that the proposed method enhances recommendation quality in terms of precision, recall, F1, and Normalized Discounted Cumulative Gain (NDCG) by 7.35%, 6.70%, 7.32% and 14.38%, respectively, when compared to other existing methodologies for food recommendation. Besides ablation study is performed to demonstrate the technical soundness of the various components of our recommendation system.http://www.sciencedirect.com/science/article/pii/S2667305322000941Recommender systemFood recommendationExplainable artificial intelligenceDeep learning |
| spellingShingle | Mehrdad Rostami Usman Muhammad Saman Forouzandeh Kamal Berahmand Vahid Farrahi Mourad Oussalah An effective explainable food recommendation using deep image clustering and community detection Intelligent Systems with Applications Recommender system Food recommendation Explainable artificial intelligence Deep learning |
| title | An effective explainable food recommendation using deep image clustering and community detection |
| title_full | An effective explainable food recommendation using deep image clustering and community detection |
| title_fullStr | An effective explainable food recommendation using deep image clustering and community detection |
| title_full_unstemmed | An effective explainable food recommendation using deep image clustering and community detection |
| title_short | An effective explainable food recommendation using deep image clustering and community detection |
| title_sort | effective explainable food recommendation using deep image clustering and community detection |
| topic | Recommender system Food recommendation Explainable artificial intelligence Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2667305322000941 |
| work_keys_str_mv | AT mehrdadrostami aneffectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT usmanmuhammad aneffectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT samanforouzandeh aneffectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT kamalberahmand aneffectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT vahidfarrahi aneffectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT mouradoussalah aneffectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT mehrdadrostami effectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT usmanmuhammad effectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT samanforouzandeh effectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT kamalberahmand effectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT vahidfarrahi effectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection AT mouradoussalah effectiveexplainablefoodrecommendationusingdeepimageclusteringandcommunitydetection |