Predicting implicit search behaviors usinglog analysis

Predicting Epidemic Tendency through Search Behavior Analysis

The possibility that influenza activity can be generally detected through search log analysis has been explored in recent years. However, previous studies have mainly focused on influenza, and little attention has been paid to other epidemics. With an analysis of web user behavior data, we consider the problem of predicting the tendency of hand-foot -and-mouth disease (HFMD), whose outbreak in ...

Modeling and Predicting Software Behaviors

Predicting Online Shopping Search Satisfaction and User Behaviors with Electrodermal Activity

Electrodermal activity (EDA) delineates positive and negative emotions, especially in the lower arousal range, which reflects small variations. This study derived formulas to extract features from the EDA graph and found they are effective to predict search satisfaction and explain mobile shopping behaviors including add to cart, purchase, and abandonment (added to cart without purchase). The b...

Predicting Film Genres with Implicit Ideals

We present a new approach to defining film genre based on implicit ideals. When viewers rate the likability of a film, they indirectly express their ideal of what a film should be. Across six studies we investigate the category structure that emerges from likability ratings and the category structure that emerges from the features of film. We further compare these data-driven category structure...

Predicting Search Task Difficulty

Search task difficulty refers to a user’s assessment about the amount of effort required to complete a search task. Our goal in this work is to learn predictive models of search task difficulty. We evaluate features derived from the user’s interaction with the search engine as well as features derived from the user’s level of interest in the task and level of prior knowledge in the task domain....