Evaluating and implementing machine learning models for personalised mobile health app recommendations.
This paper focuses on the evaluation and recommendation of healthcare applications in the mHealth field. The increase in the use of health applications, supported by an expanding mHealth market, highlights the importance of this research. In this study, a data set including app descriptions, ratings...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0319828 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327790628798464 |
|---|---|
| author | Hafsat Morenigbade Tareq Al Jaber Neil Gordon Gregory Eke |
| author_facet | Hafsat Morenigbade Tareq Al Jaber Neil Gordon Gregory Eke |
| author_sort | Hafsat Morenigbade |
| collection | DOAJ |
| description | This paper focuses on the evaluation and recommendation of healthcare applications in the mHealth field. The increase in the use of health applications, supported by an expanding mHealth market, highlights the importance of this research. In this study, a data set including app descriptions, ratings, reviews, and other relevant attributes from various health app platforms was selected. The main goal was to design a recommendation system that leverages app attributes, especially descriptions, to provide users with relevant contextual suggestions. A comprehensive pre-processing regime was carried out, including one-hot encoding, standardisation, and feature engineering. The feature, "Rating_Reviews", was introduced to capture the cumulative influence of ratings and reviews. The variable 'Category' was chosen as a target to discern different health contexts such as 'Weight loss' and 'Medical'. Various machine learning and deep learning models were evaluated, from the baseline Random Forest Classifier to the sophisticated BERT model. The results highlighted the efficiency of transfer learning, especially BERT, which achieved an accuracy of approximately 90% after hyperparameter tuning. A final recommendation system was designed, which uses cosine similarity to rank apps based on their relevance to user queries. |
| format | Article |
| id | doaj-art-ed0ddd4856a74c19bcddabdd3e500543 |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-ed0ddd4856a74c19bcddabdd3e5005432025-08-20T03:47:45ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e031982810.1371/journal.pone.0319828Evaluating and implementing machine learning models for personalised mobile health app recommendations.Hafsat MorenigbadeTareq Al JaberNeil GordonGregory EkeThis paper focuses on the evaluation and recommendation of healthcare applications in the mHealth field. The increase in the use of health applications, supported by an expanding mHealth market, highlights the importance of this research. In this study, a data set including app descriptions, ratings, reviews, and other relevant attributes from various health app platforms was selected. The main goal was to design a recommendation system that leverages app attributes, especially descriptions, to provide users with relevant contextual suggestions. A comprehensive pre-processing regime was carried out, including one-hot encoding, standardisation, and feature engineering. The feature, "Rating_Reviews", was introduced to capture the cumulative influence of ratings and reviews. The variable 'Category' was chosen as a target to discern different health contexts such as 'Weight loss' and 'Medical'. Various machine learning and deep learning models were evaluated, from the baseline Random Forest Classifier to the sophisticated BERT model. The results highlighted the efficiency of transfer learning, especially BERT, which achieved an accuracy of approximately 90% after hyperparameter tuning. A final recommendation system was designed, which uses cosine similarity to rank apps based on their relevance to user queries.https://doi.org/10.1371/journal.pone.0319828 |
| spellingShingle | Hafsat Morenigbade Tareq Al Jaber Neil Gordon Gregory Eke Evaluating and implementing machine learning models for personalised mobile health app recommendations. PLoS ONE |
| title | Evaluating and implementing machine learning models for personalised mobile health app recommendations. |
| title_full | Evaluating and implementing machine learning models for personalised mobile health app recommendations. |
| title_fullStr | Evaluating and implementing machine learning models for personalised mobile health app recommendations. |
| title_full_unstemmed | Evaluating and implementing machine learning models for personalised mobile health app recommendations. |
| title_short | Evaluating and implementing machine learning models for personalised mobile health app recommendations. |
| title_sort | evaluating and implementing machine learning models for personalised mobile health app recommendations |
| url | https://doi.org/10.1371/journal.pone.0319828 |
| work_keys_str_mv | AT hafsatmorenigbade evaluatingandimplementingmachinelearningmodelsforpersonalisedmobilehealthapprecommendations AT tareqaljaber evaluatingandimplementingmachinelearningmodelsforpersonalisedmobilehealthapprecommendations AT neilgordon evaluatingandimplementingmachinelearningmodelsforpersonalisedmobilehealthapprecommendations AT gregoryeke evaluatingandimplementingmachinelearningmodelsforpersonalisedmobilehealthapprecommendations |