On Learning Researchers´ Dynamic Information Needs: An Entropy-Based Query Expansion Approach

Literature survey is one of the most important steps in the process of academic research, allowing researchers to explore and understand topics. However, researchers without sufficient prior knowledge lack the skills to determine proper and accurate keywords for investigating the topics at hand. To tackle this problem, we proposed an entropy-based query expansion with a reweigh ting (E_QE) approach to revise queries during the iterative retrieval process. We designed a series of experiments that consider the researcher´s changing information needs during task execution. Two topic change situations are considered in this work¡Xboth minor, and dramatic topic changes. The simulation-based pseudo-relevance feedback technique is applied during the search process to evaluate the effectiveness of the proposed approach without the intervention of human efforts. We measured the effectiveness of the TFIDF and E_QE approaches for different types of topic change situations. The preliminary results show that the proposed query expansion approach can achieve better results, helping researchers to revise queries.