An Effective Segmentation of User Search Interests Based On Task Track

Arati A. Topai, A. B. Rajmane

Abstract


Web logs record the users search queries and related actions in search engines. It is possible to understand user search behaviors by mining these information. A task can be defined as atomic user information need, whereas a task track represents activities of all user within that particular task, such as query reformulations, URL clicks. In the previous works, web logs have been studied at session, query or task level where users have to submit several queries within one task and handle several tasks within a session. Although previous studies have addressed the problem i.e. identification of task, little is known about the advantage of using task over session or query for search applications. It is defined to conduct immense analyses and comparisons to evaluate the efficacy of task track in search applications: user satisfaction determination, user search interest’s prediction and related query suggestions.

Keywords- log analysis, Search log mining, Task Track


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v7i2.2626

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science