A mouse-trajectory based model for predicting query-URL relevance
For the learning-to-ranking algorithms used in commercial search engines, a conventional way to generate the training examples is to employ professional annotators to label the relevance of query-url pairs. Since label quality depends on the expertise of annotators to a large extent, this process is...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/104498 http://hdl.handle.net/10220/18850 http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/4968 |
| _version_ | 1811689452078104576 |
|---|---|
| author | Song, Hengjie Liao, Ruoxue Zhang, Xiangliang Yang, Qiang Miao, Chun Yan |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Song, Hengjie Liao, Ruoxue Zhang, Xiangliang Yang, Qiang Miao, Chun Yan |
| author_sort | Song, Hengjie |
| collection | NTU |
| description | For the learning-to-ranking algorithms used in commercial search engines, a conventional way to generate the training examples is to employ professional annotators to label the relevance of query-url pairs. Since label quality depends on the expertise of annotators to a large extent, this process is time-consuming and labor-intensive. Automatically generating labels from click-through data has been well studied to have comparable or better performance than human judges. Click-through data present users’ action and imply their satisfaction on search results, but exclude the interactions between users and search results beyond the page-view level (e.g., eye and mouse movements). This paper proposes a novel approach to comprehensively consider the information underlying mouse trajectory and click-through data so as to describe user behaviors more objectively and achieve a better understanding of the user experience. By integrating multi-sources data, the proposed approach reveals that the relevance labels of query-url pairs are related to positions of urls and users’ behavioral features. Based on their correlations, query-url pairs can be labeled more accurately and search results are more satisfactory to users. The experiments that are conducted on the most popular Chinese commercial search engine (Baidu) validated the rationality of our research motivation and proved that the proposed approach outperformed the state-of-the-art methods. |
| first_indexed | 2024-10-01T05:48:19Z |
| format | Conference Paper |
| id | ntu-10356/104498 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:48:19Z |
| publishDate | 2014 |
| record_format | dspace |
| spelling | ntu-10356/1044982020-05-28T07:18:14Z A mouse-trajectory based model for predicting query-URL relevance Song, Hengjie Liao, Ruoxue Zhang, Xiangliang Yang, Qiang Miao, Chun Yan School of Computer Engineering Conference on Artificial Intelligence (26th : 2012) DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence For the learning-to-ranking algorithms used in commercial search engines, a conventional way to generate the training examples is to employ professional annotators to label the relevance of query-url pairs. Since label quality depends on the expertise of annotators to a large extent, this process is time-consuming and labor-intensive. Automatically generating labels from click-through data has been well studied to have comparable or better performance than human judges. Click-through data present users’ action and imply their satisfaction on search results, but exclude the interactions between users and search results beyond the page-view level (e.g., eye and mouse movements). This paper proposes a novel approach to comprehensively consider the information underlying mouse trajectory and click-through data so as to describe user behaviors more objectively and achieve a better understanding of the user experience. By integrating multi-sources data, the proposed approach reveals that the relevance labels of query-url pairs are related to positions of urls and users’ behavioral features. Based on their correlations, query-url pairs can be labeled more accurately and search results are more satisfactory to users. The experiments that are conducted on the most popular Chinese commercial search engine (Baidu) validated the rationality of our research motivation and proved that the proposed approach outperformed the state-of-the-art methods. 2014-02-19T05:44:41Z 2019-12-06T21:34:07Z 2014-02-19T05:44:41Z 2019-12-06T21:34:07Z 2012 2012 Conference Paper Song, H., Liao, R., Zhang, X., Miao, C., & Yang, Q. (2012). A mouse-trajectory based model for predicting query-URL relevance. Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, 143-149. https://hdl.handle.net/10356/104498 http://hdl.handle.net/10220/18850 http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/4968 en © 2012 Association for the Advancement of Artificial Intelligence. |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Song, Hengjie Liao, Ruoxue Zhang, Xiangliang Yang, Qiang Miao, Chun Yan A mouse-trajectory based model for predicting query-URL relevance |
| title | A mouse-trajectory based model for predicting query-URL relevance |
| title_full | A mouse-trajectory based model for predicting query-URL relevance |
| title_fullStr | A mouse-trajectory based model for predicting query-URL relevance |
| title_full_unstemmed | A mouse-trajectory based model for predicting query-URL relevance |
| title_short | A mouse-trajectory based model for predicting query-URL relevance |
| title_sort | mouse trajectory based model for predicting query url relevance |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/104498 http://hdl.handle.net/10220/18850 http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/view/4968 |
| work_keys_str_mv | AT songhengjie amousetrajectorybasedmodelforpredictingqueryurlrelevance AT liaoruoxue amousetrajectorybasedmodelforpredictingqueryurlrelevance AT zhangxiangliang amousetrajectorybasedmodelforpredictingqueryurlrelevance AT yangqiang amousetrajectorybasedmodelforpredictingqueryurlrelevance AT miaochunyan amousetrajectorybasedmodelforpredictingqueryurlrelevance AT songhengjie mousetrajectorybasedmodelforpredictingqueryurlrelevance AT liaoruoxue mousetrajectorybasedmodelforpredictingqueryurlrelevance AT zhangxiangliang mousetrajectorybasedmodelforpredictingqueryurlrelevance AT yangqiang mousetrajectorybasedmodelforpredictingqueryurlrelevance AT miaochunyan mousetrajectorybasedmodelforpredictingqueryurlrelevance |