Supporting Exploratory Search Research Articles

A New Query Recommendation Method Supporting Exploratory Search Based on Search Goal Shift Graphs

Exploratory search is an increasingly important activity for Web searchers. However, the current search system can not provide sufficient support for exploratory search. Therefore, we made in-depth analysis for exploratory search processes, and found that there are a lot of search goal shift phenomena in exploratory search. Based on this fact, we have designed a new query recommendation method to support exploratory search. Firstly, according to the behavioral characteristics of searchers in the search goal shift processes, all the queries submitted in the search goal shift processes are extracted from search engine logs using machine learning. And then, we have used the queries to build a search goal shift graph; finally, the random walk algorithm is used to obtain the query recommendations in the search goal shift graph. In addition, we demonstrated the effectiveness of the method for exploratory search by comparing experiments with the other methods.

Supporting Exploratory Search with a Visual User-Driven Approach

Whenever users engage in gathering and organizing new information, searching and browsing activities emerge at the core of the exploration process. As the process unfolds and new knowledge is acquired, interest drifts occur inevitably and need to be accounted for. Despite the advances in retrieval and recommender algorithms, real-world interfaces have remained largely unchanged: results are delivered in a relevance-ranked list. However, it quickly becomes cumbersome to reorganize resources along new interests, as any new search brings new results. We introduce an interactive user-driven tool that aims at supporting users in understanding, refining, and reorganizing documents on the fly as information needs evolve. Decisions regarding visual and interactive design aspects are tightly grounded on a conceptual model for exploratory search. In other words, the different views in the user interface address stages of awareness, exploration, and explanation unfolding along the discovery process, supported by a set of text-mining methods. A formal evaluation showed that gathering items relevant to a particular topic of interest with our tool incurs in a lower cognitive load compared to a traditional ranked list. A second study reports on usage patterns and usability of the various interaction techniques within a free, unsupervised setting.

Supporting exploratory search tasks with interactive user modeling

AbstractThis paper presents the design and study of interactive user modeling to support exploratory search tasks. Contrary to traditional interactions, such as query based search, query suggestions, or relevance feedback, interactive user modeling allows a user to perceive the state of the user model at all times and provide feedback that directly rewards or penalizes it. The technique allows the user to continuously tune the system's belief about the user's evolving information needs. We demonstrate that such functionality is useful in exploratory search where users need to get accustomed to a body of literature in a domain. We conducted two experiments where scientists carried out exploratory search tasks with our implementation of an interactive user modeling and retrieval system (SciNet) and two baselines: SciNet from which interactive user modeling was excluded and a real‐world baseline (Google Scholar). The results show that interactive user modeling can help users to more effectively find relevant, novel and diverse information without compromises in task execution time.

Exploring web neighbours in exploratory search

PurposeAccess to related information is a key requirement for exploratory search. The purpose of this research is to understand where related information may be found and how it may be explored by users.Design/methodology/approachEarlier research provides sufficient evidence that web graph neighborhoods of returned search results may contain documents related to users' intended search topic. However, in the literature, no interface mechanisms have been presented to enable exploration of these neighborhoods by users. Based on a modified web graph, this paper proposes tools and methods for displaying and exploring the graph neighborhood of any selected item in the search results list. Important issues that arise when implementing such an exploration model are discussed and utility of the proposed system is evaluated with user experiments.FindingsIn user experiments first, information related to intended search topic was often found in the web neighborhood of search results; second, exploring these graph neighborhoods with the proposed tools improved users' ability to reach the information they sought.Research limitations/implicationsThe test participants are computer science graduate students. Their skills may not be representative of the broad user population.Originality/valueThe lessons learned from this research point to a potentially fruitful direction for designing new search engine interfaces that support exploratory search.