Influences on Query Reformalution in Collaborative Web Search

Zhen Yue, Shuguang Han, Daqing He, and Jiepu Jiang (Computer-2014)
http://ieeexplore.ieee.org/abstract/document/6766167/
In the paper “Influences on Query Reformation in Collaborative Web Search”, Yue et al. investigate a study to analyze the influences of collaboration between members in a group for information seeking. They are motivated to study (1) the influence of collaboration on search query formulation and reformulation; (2) similarities and differences exist in terms of query reformulation for collaborative searches compared with individual searches; and (3) the nature of the query task influence query reformulation in collaborative information seeking (CIS).
In order to run the study, Yue et al. used CollabSearch, a Web search system developed by their group for collaborative users. The system includes three frames: a topic statement page which shows the description about the search task a group want to conduct; a web search page which displays Google search results for each query; and a team workspace page where stores the saved webpages or snippets of pages within their group and other relevant information. Moreover, the system also provides teammates with a chat box for communication.
For the study design and implementation, they recruited 20 University of Pittsburgh students (10 males and 10 females). The participants registered the study as pairs, and members of each pair already know each one. As members of group, each teammate has access to one another’s search histories and shared results. For communication, they can only use text messages/chat, no face-to-face communication was allowed. All pairs are assigned to the two exploratory Web searches (an academic search and a leisure activity search), and team members worked on together simultaneously. The participants were trained 15 minutes before working on the tasks (i.e., 30 minutes per each task). After completing the tasks, they did a post-search questionnaire and interviews about their search process, strategies and experiences.
After collecting all necessary data for their study, Yue et al. perform three data analysis methods which are:
  • Query log analysis: examine the influence of search activities and collaborative activities on the generation of new query terms
  • Questionnaire analysis: participants self-reported what they perceived as the influences on their query reformulations
  • Text message content analysis: determine the effect of explicit communication on participants’ query reformulations

The results from their study suggest three kinds of influence on query reformulation in CIS. The first factor influence reformulating queries is actions related to a participant’s own search process, including viewing prior search results, saving prior search results, and prior query terms (search history). Secondly, collaborative actions also influence query reformulation. The collaborative actions include (1) a participant checking his or her partner’s saved documents in the shared workspace; (2) a participant checking the partner’s query history; (3) explicit communication between the partners through text messaging/chat. Yue et al. found the strong influence of explicit communication between partners on query reformulation for the leisure activity search; however, this influence is significantly lower for the academic search. Additionally, they also found the influence of a partner’s search history on generating new query terms and the importance of the shared workplace for an academic search (i.e., a recall-oriented, information-gathering task). Finally, based on message content analysis, they claim that about 78 percent of queries for both kinds of tasks could be related to chat. However, this findings doesn’t consist with participants’ self-reporting. They explained that this disparity probably results from the fact that participants did not link an indirect influence that occurred during partner communication to their query reformulation.

Comments

Post a Comment

Popular posts from this blog

Personalized Access to Scientific Publications: from Recommendation to Explanation

Dario De Nart, Felice Ferrara, and Carlo Tasso ( UMAP-2013 ) http://link.springer.com/chapter/10.1007/978-3-642-38844-6_26 In the paper “Personalized Access to Scientific Publications: from Recommendation to Explanation”, Dario De Nart et al. present a Recommender and Explanation System (RES) that is able to recommend scientific publication and show explanation to users.  In order to do recommendation, Dario De Nart et al., firstly, use the The Dikpe Keyphrase extraction algorithm introduced by Pudota (2010) to extract keyphrases from papers. Each keyphrase has a weight called keyphraseness that reveals the several lexical and statistical indicators exploited in the extraction process. Higher is the keyphraseness, more relevant is the KP. For each paper in the collection, they represent it as a conceptual graph. Each node in the graph is a term broken down from a KP. Two nodes are connected when they appear in the same KP. For instance, the KP “document retrieval” is split int...
Read more

SoRec: Social Recommendation Using Probabilistic Matrix Factorization

Hao Ma, Haixuan Yang, Michael R. Lyu, Irwin King ( CIKM-08 ) http://dl.acm.org/citation.cfm?id=1458205 In this paper, Hao Ma et al. present an approach that help to deal with very large datasets and users who have made few ratings in recommender systems. Traditional methods (e.g., Pearson Correlation Coefficient and Cosine) assume that two users have rated at least some items in common so that they can compute the similarity of these users. Thus, memory-based and model-based collaborative filtering algorithms fail to find similarities of users who have never rated any items. In daily life, people usually ask their family or friends for recommendations of new movies, songs, books, restaurants or places to visit. Therefore, the authors propose a factor analysis approach based on probabilistic matrix factorization to solve the data sparsity and poor prediction accuracy problems by employing both users’ social network information and rating records. Different with traditional persp...
Read more