Using Program Synthesis for Social Recommendations
This paper presents a new approach to select events of interest to a user in a social media setting where events are generated by the activities of the user's friends through their mobile devices. We argue that given the unique requirements of the social media setting, the problem is best viewe...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Language: | en-US |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/72106 |
| _version_ | 1826206391500537856 |
|---|---|
| author | Cheung, Alvin Solar-Lezama, Armando Madden, Samuel |
| author2 | Armando Solar-Lezama |
| author_facet | Armando Solar-Lezama Cheung, Alvin Solar-Lezama, Armando Madden, Samuel |
| author_sort | Cheung, Alvin |
| collection | MIT |
| description | This paper presents a new approach to select events of interest to a user in a social media setting where events are generated by the activities of the user's friends through their mobile devices. We argue that given the unique requirements of the social media setting, the problem is best viewed as an inductive learning problem, where the goal is to first generalize from the users' expressed "likes" and "dislikes" of specific events, then to produce a program that can be manipulated by the system and distributed to the collection devices to collect only data of interest. The key contribution of this paper is a new algorithm that combines existing machine learning techniques with new program synthesis technology to learn users' preferences. We show that when compared with the more standard approaches, our new algorithm provides up to order-of-magnitude reductions in model training time, and significantly higher prediction accuracies for our target application. The approach also improves on standard machine learning techniques in that it produces clear programs that can be manipulated to optimize data collection and filtering. |
| first_indexed | 2024-09-23T13:29:08Z |
| id | mit-1721.1/72106 |
| institution | Massachusetts Institute of Technology |
| language | en-US |
| last_indexed | 2024-09-23T13:29:08Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | mit-1721.1/721062019-04-10T14:00:14Z Using Program Synthesis for Social Recommendations Cheung, Alvin Solar-Lezama, Armando Madden, Samuel Armando Solar-Lezama Computer-Aided Programming recommender systems social networking applications support vector machines This paper presents a new approach to select events of interest to a user in a social media setting where events are generated by the activities of the user's friends through their mobile devices. We argue that given the unique requirements of the social media setting, the problem is best viewed as an inductive learning problem, where the goal is to first generalize from the users' expressed "likes" and "dislikes" of specific events, then to produce a program that can be manipulated by the system and distributed to the collection devices to collect only data of interest. The key contribution of this paper is a new algorithm that combines existing machine learning techniques with new program synthesis technology to learn users' preferences. We show that when compared with the more standard approaches, our new algorithm provides up to order-of-magnitude reductions in model training time, and significantly higher prediction accuracies for our target application. The approach also improves on standard machine learning techniques in that it produces clear programs that can be manipulated to optimize data collection and filtering. 2012-08-13T21:15:04Z 2012-08-13T21:15:04Z 2012-08-13 http://hdl.handle.net/1721.1/72106 en-US MIT-CSAIL-TR-2012-025 Creative Commons Attribution 3.0 Unported http://creativecommons.org/licenses/by/3.0/ 10 p. application/pdf |
| spellingShingle | recommender systems social networking applications support vector machines Cheung, Alvin Solar-Lezama, Armando Madden, Samuel Using Program Synthesis for Social Recommendations |
| title | Using Program Synthesis for Social Recommendations |
| title_full | Using Program Synthesis for Social Recommendations |
| title_fullStr | Using Program Synthesis for Social Recommendations |
| title_full_unstemmed | Using Program Synthesis for Social Recommendations |
| title_short | Using Program Synthesis for Social Recommendations |
| title_sort | using program synthesis for social recommendations |
| topic | recommender systems social networking applications support vector machines |
| url | http://hdl.handle.net/1721.1/72106 |
| work_keys_str_mv | AT cheungalvin usingprogramsynthesisforsocialrecommendations AT solarlezamaarmando usingprogramsynthesisforsocialrecommendations AT maddensamuel usingprogramsynthesisforsocialrecommendations |