Have you ever wondered that people are increasingly using Web Search Engines for performing their tasks, such as “planning holidays” or “organizing birthday parties“, rather than barely lookup for Web pages?
Although search engines nowadays offer several mechanisms to help their users (e.g., query suggestion, search-as-you-type, result diversification, etc.), in essence they are document retrieval systems that answer a user query with a simple list of “ten blue links“.
We believe next-generation search engines should progress from being mere Web document retrieval tools to becoming multifaceted systems, which fully support users while they are interacting with the Web. This creates novel and exciting research challenges ranging from the ability to recognize latent tasks from the issued queries, to the design of new recommendation strategies and user interfaces for showing relevant results.
In this work, we first discuss a two-step query clustering methodology to discover the latent tasks performed by users from query logs. Furthermore, we introduce the Task Relation Graph (TRG) as a representation of users’ search behaviors on a task-by-task perspective. The task-by-task behavior is captured by weighting the edges of TRG with a relatedness score computed between pairs of tasks, as mined from the query log.
We firstly validate the ability of our approach to effectively discover latent tasks from query logs.
Furthermore, we evaluate its performance when used for implementing a concrete, newly-introduced application, namely a task recommender system, which suggests related tasks to users on the basis of the task predictions derived from the TRG. Finally, we show that the task recommendations generated by our solution are beyond the reach of existing query suggestion schemes, and that our method recommends tasks that user will likely perform in the near future.
- Lucchese, C., Orlando, S., Perego, R., Silvestri, F., and Tolomei, G. Discovering User Tasks from Search Engine Query Logs. In ACM Transactions on Information Systems (ACM TOIS), vol. 31, issue 3 – July 2013, pp. 14:1–14:43.
- Lucchese, C., Orlando, S., Perego, R., Silvestri, F., and Tolomei, G. Modeling and Predicting the Task-by-Task Behavior of Search Engine Users. In Proceedings of the International Conference on Open Research Areas in Information Retrieval, OAIR 2013, pp. 77–84.
- Lucchese, C., Orlando, S., Perego, R., Silvestri, F., and Tolomei, G. Identifying Task-based Sessions in Search Engine Query Logs. In Proceedings of the ACM International Conference on Web Search and Data Mining, WSDM 2011, pp. 277–286 [best paper runner up].