Contextual Reasoning based Mobile Recommender System
Ladda ner
Typ
Examensarbete för masterexamen
Master Thesis
Master Thesis
Program
Publicerad
2012
Författare
Gupta, Abhiroop
Modellbyggare
Tidskriftstitel
ISSN
Volymtitel
Utgivare
Sammanfattning
With the ever increasing popularity of Smartphone and reducing charges for device and data Mobile applications users are estimated to quadruple in the next three years. With the increase in the number of users Applications in the market are increasing by thousands every day. The Users are flooded with so much of choices that it is hard for them to find appropriate and Suitable apps. Recommender systems can aid the users in discovering new applications in a personalized manner. The purpose of this thesis is to investigate how to enhance the recommendations to a user in the process of discovering new mobile applications by better utilization of context data available through various sensors in a modern day Smartphone. The work of the thesis is divided into three phases where the aim of the first phase is to study related work and related systems to identify promising concepts and features. During the second phase, a prototype system is designed and implemented. The outcome and result of the first two phases is then evaluated and analyzed in the third and final phase. The prototype system integrates an existing mobile app recommender system to add the features of context awareness and context reasoning. The major draw of the thesis is to suitably define context and situations of interests and model them appropriately. Learning techniques are applied to learn these models using the context data generated by the user. The derived situation provides an added parameter in the process of information filtering in a personalized manner.
Beskrivning
Ämne/nyckelord
Människa-datorinteraktion (interaktionsdesign) , Informations- och kommunikationsteknik , Human Computer Interaction , Information & Communication Technology