Implicit Profiling for Contextual Reasoning About Users' Spatial Preferences
نویسندگان
چکیده
Information overload is a well documented problem in many application domains. A way of addressing this problem is by creating user profiles and by filtering out all irrelevant information while presenting the users only with information that matches their interests. Our focus is on the spatial domain. We follow an implicit profiling approach by logging users’ mouse movements as they interact with spatial data. The logged information is analysed to support context reasoning about each user’s level of interest in the spatial features shown to him. These inferred interests are used to calculate an interest model for each individual user. Based on this interest model we can filter the information returned to the user, reducing information overload and tailoring the content to suit the users spatial preferences. In this paper we present our approach and discuss the implementation of the system we are developing for capturing users’ spatial interactions and generating user profiles.
منابع مشابه
Profiling Nomadic Users Considering Preferences and Context of Use
In order to adapt information for a nomadic user equipped with a Mobile Device (MD), an Information System (IS) must take into consideration data that deals with the context of use and user preferences. Data about context of use provides in particular a description of the conditions (temporal, spatial, hardware, etc.) under which users accesses the IS. Data about user preferences aims at expres...
متن کاملUser profiling with Case-Based Reasoning and Bayesian Networks
Agent technology provides many services to users. The tasks in which agents are involved include information filtering, information retrieval, user's tasks automation, browsing assistance and so on. In order to assist users, agents have to learn their preferences. These preferences are represented by user profiles. Many techniques have been developed for user profiling, which vary from statisti...
متن کاملNeural Endorsement Based Contextual Suggestion
This paper presents the University of Amsterdam’s participation in the TREC 2016 Contextual Suggestion Track. In this research, we have studied a personallized neural document language modeling and a neural category preference modeling for contextual suggestion using available endorsements in TREC 2016 contextual suggestion track phase 2 requests. Specifically, our main aim is to answer the que...
متن کاملTowards Time-Dependant Recommendation based on Implicit Feedback
Context-aware recommender systems (CARS) aim at improving users’ satisfaction by tailoring recommendations to each particular context. In this work we propose a contextual pre-filtering technique based on implicit user feedback. We introduce a new context-aware recommendation approach called user micro-profiling. We split each single user profile into several possibly overlapping sub-profiles, ...
متن کاملA Service for Aggregating and Interpreting Contextual Information
contextaware computing, Me-Centric computing, ontology, reasoning, web services, semantic web We present an architectural support for building context-aware applications. With the increasing acceptance of dynamic mobile and ubiquitous computing environments, applications are no longer limited to relying only on the information explicitly provided by users. Instead, these environments invite a n...
متن کامل