Abstract | ||
---|---|---|
In this paper, we introduce "task trail" as a new concept to understand user search behaviors. We define task to be an atomic user information need. Web search logs have been studied mainly at session or query level where users may submit several queries within one task and handle several tasks within one session. Although previous studies have addressed the problem of task identification, little is known about the advantage of using task over session and query for search applications. In this paper, we conduct extensive analyses and comparisons to evaluate the effectiveness of task trails in three search applications: determining user satisfaction, predicting user search interests, and query suggestion. Experiments are conducted on large scale datasets from a commercial search engine. Experimental results show that: (1) Sessions and queries are not as precise as tasks in determining user satisfaction. (2) Task trails provide higher web page utilities to users than other sources. (3) Tasks represent atomic user information needs, and therefore can preserve topic similarity between query pairs. (4) Task-based query suggestion can provide complementary results to other models. The findings in this paper verify the need to extract task trails from web search logs and suggest potential applications in search and recommendation systems. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2187836.2187903 | WWW |
Keywords | Field | DocType |
atomic user information need,task trail,task identification,search application,user search interest,user satisfaction,web search log,search task,commercial search engine,task-based query suggestion,user search behavior,information need,recommender system,web pages,search engine | Web search query,Data mining,World Wide Web,Search engine,Task analysis,Information retrieval,Query expansion,Web page,Computer science,Web query classification,User information,Search analytics | Conference |
Citations | PageRank | References |
36 | 1.18 | 33 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhen Liao | 1 | 405 | 13.33 |
Yang Song | 2 | 2338 | 128.89 |
Li-wei He | 3 | 1943 | 165.91 |
Yalou Huang | 4 | 744 | 53.86 |