|Ph.D Student||Kravi Elad|
|Subject||Understanding the Context of Microactions on the Web|
|Department||Department of Computer Science||Supervisors||Professor Benny Kimelfeld|
|Dr. Yaron Kanza|
|Full Thesis text|
With the wide usage of smartphones, there is a constant increase in user interaction with web applications like microblogs and search engines. Examples of such interactions, referred to as microactions, include posing a query, sending a textual message, sharing a photo, etc. Analysis of microactions is beneficial for understanding the context of a microaction and can be used for improving existing services and offering new ones. For example, by detecting whether a search is performed from a location that is familiar to the user or not, search engines can adjust their results and better answer the information need.
In this study, we investigate the challenge of discovering information about the context of microactions. For example, is the user at a shopping mall or at school? Is she conducting the search from home or from a place she is not familiar with? Where is she likely to visit next? Is the search a single atomic action or part of a session? We examined a variety of sources (microblogs, logs of a web search engine, etc.). We studied classification of location type based on geo-tagged posts, discovery of links between pairs of locations where people who visit one location are likely to visit the other, distinction between web search from a familiar place and search from an unfamiliar place, and prediction of the number of clicks a search query will be associated with. The study shows that we can discover valuable information about the microaction context and use it in a variety of ways, to improve web applications.