Most present day search engines have a deterministic behavior in the sense that they return the same search results for all users who submit the same query at a certaintime. They do not take the users interests and preferences into account in the retrievalprocess. Integrating user context in the retrieval process can help deliver more targetedsearch results, thereby providing a personalized search experience to the user. Personalizing web search involves the process of identifying user interests duringinteraction with the user, and then using that information to deliver results that are morerelevant to the user. In this thesis, we present our approach to personalizing web searchon a mobile device (iPhone). Our approach involves building an ontological model ofuser interests on the users mobile device based on his interaction with web searchresults. Personalization of search results is achieved by re-ranking search resultsreturned by a standard search engine (Yahoo) based on proximity to the users interestmodel. The ability to recognize user interests in a completely non-invasive way and theaccuracy of personalized results are some of the major advantages of our approach.