אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

The wide usage of smartphones encourages users to ubiquitously and constantly interact with web applications like microblogs and search engines. Examples of atomic interactions, referred as micro-actions, include posing a query, sending a textual message, sharing a photo etc. Analysis of micro-actions is beneficial for understanding the context of a micro-action 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 show how to discover information about the context of micro-actions in order to infer useful information about this context. For example, is the user at a shopping mall or at school? Where is she likely to visit next? Is she conducting the search from home or from a place she is not familiar with? 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, distinguishing between web search from a familiar place and search from an unfamiliar place, and predicting the number of clicks a search query will be associated with. The study shows that the context of micro-actions on the web can be detected and used in a variety of ways, to improve webapplications.