We present a very different cause of search engine user behaviors ——fascination. It is generally identified as the initial effect of a product attribute on users' interest and purchase intentions. Considering th...We present a very different cause of search engine user behaviors ——fascination. It is generally identified as the initial effect of a product attribute on users' interest and purchase intentions. Considering the fact that in most cases the cursor is driven directly by a hand to move via a mouse (or touchpad), we use the cursor movement as the critical feature to analyze the personal reaction against the fascinating search results. This paper provides a deep insight into the goal-directed cursor movement that occurs within a remarkably short period of time (<30 milliseconds), which is the interval between a user's click-through and decision-making behaviors. Instead of the fundamentals, we focus on revealing the characteristics of the split-second cursor movement. Our empirical findings showed that a user may push or pull the mouse with a slightly greater strength when fascinated by a search result. As a result, the cursor slides toward the search result with an increased momentum. We model the momentum through a combination of translational and angular kinetic energy calculations. Based on Fitts' law, we implement goal-directed cursor movement identification. Supported by the momentum, together with other physical features, we built different fascination-based search result reranking systems. Our experiments showed that goal-directed cursor momentum is an effective feature in detecting fascination. In particular, they show feasibility in both the personalized and cross-media cases. In addition, we detail the advantages and disadvantages of both click-through rate and cursor momentum for re-ranking search results.展开更多
近年来在信息检索领域研究人员提出了多种支持结果多样化的排名算法,但还没有相关文献对这些算法的性能进行系统的分析和比较。为此,在数据融合排名算法Comb Sum的基础上,提出一种同时考虑文档相关性和多样性的排名算法Comb Sum Div,并...近年来在信息检索领域研究人员提出了多种支持结果多样化的排名算法,但还没有相关文献对这些算法的性能进行系统的分析和比较。为此,在数据融合排名算法Comb Sum的基础上,提出一种同时考虑文档相关性和多样性的排名算法Comb Sum Div,并将其与x Qu AD和PM2这2种显式排名算法进行性能比较。在TREC多样性任务提供的查询数据集和Clue Web09B数据集上的实验结果表明,Comb Sum Div查询性能较优、x Qu AD次之、PM2较差,且3种算法均具有较强的稳定性及抗干扰能力。展开更多
基金the National Natural Science Foundation of China (Grant Nos. 61672368, 61373097, and 61672367)the Research Foundation of the Ministry of Education and China Mobile (MCM20150602)the Science and Technology Plan of Jiangsu (BK20151222).
文摘We present a very different cause of search engine user behaviors ——fascination. It is generally identified as the initial effect of a product attribute on users' interest and purchase intentions. Considering the fact that in most cases the cursor is driven directly by a hand to move via a mouse (or touchpad), we use the cursor movement as the critical feature to analyze the personal reaction against the fascinating search results. This paper provides a deep insight into the goal-directed cursor movement that occurs within a remarkably short period of time (<30 milliseconds), which is the interval between a user's click-through and decision-making behaviors. Instead of the fundamentals, we focus on revealing the characteristics of the split-second cursor movement. Our empirical findings showed that a user may push or pull the mouse with a slightly greater strength when fascinated by a search result. As a result, the cursor slides toward the search result with an increased momentum. We model the momentum through a combination of translational and angular kinetic energy calculations. Based on Fitts' law, we implement goal-directed cursor movement identification. Supported by the momentum, together with other physical features, we built different fascination-based search result reranking systems. Our experiments showed that goal-directed cursor momentum is an effective feature in detecting fascination. In particular, they show feasibility in both the personalized and cross-media cases. In addition, we detail the advantages and disadvantages of both click-through rate and cursor momentum for re-ranking search results.
