A Method for Detecting Behavior-Based User Profiles in Collaborative Ontology Engineering
نویسندگان
چکیده
Collaborative ontology-engineering methods usually prescribe a set of processes, activities, types of stakeholders and the roles each stakeholder plays in these activities. We, however, believe that the stakeholder community of each ontology-engineering project is different and one can therefore observe different types of user behavior. It may thus very well be that the prescribed set of stakeholder types and roles do not suffice. If one were able to identify these user behavior types, which we will call a user profile, one can compliment or revisit those predefined roles. For instance, those user profiles can be used to provide customized interfaces for optimizing activities in certain ontology-engineering projects. We present a method that discovers different user profiles based on the interactions users have with each other in a collaborative ontology-engineering environment. Our approach clusters the users based on the types of interactions they perform, which are retrieved from datasets that were annotated with an interaction ontology – built on top of SIOC – that we have developed. We demonstrate our method using the database of two instances of the GOSPL ontologyengineering tool. The databases contain the interactions of two distinct ontology-engineering projects involving S. Van Laere · R. Buyl · M. Nyssen Vrije Universiteit Brussel, Department of Public Health, Biostatistics and Medical Informatics (BISI) Research Group, Laarbeeklaan 103, 1090 Jette, Belgium Tel.: +32-2-477-4444, Fax: +32-2-477-4000, E-mail: {svvlaere,rbuyl,mnyssen}@vub.ac.be C. Debruyne ADAPT Centre, Trinity College Dublin, Dublin 2, Ireland WISE Lab, Vrije Universiteit Brussel, Brussels, Belgium E-mail: [email protected] respectively 42 and 36 users. For each dataset, we discuss the findings by analyzing the different clusters. We found that we are able to discover different user profiles, indicating that the approach we have taken is viable, though more experiments are needed to validate the results.
منابع مشابه
An ontological hybrid recommender system for dealing with cold start problem
Recommender Systems ( ) are expected to suggest the accurate goods to the consumers. Cold start is the most important challenge for RSs. Recent hybrid s combine and . We introduce an ontological hybrid RS where the ontology has been employed in its part while improving the ontology structure by its part. In this paper, a new hybrid approach is proposed based on the combination of demog...
متن کاملA Novel Trust Computation Method Based on User Ratings to Improve the Recommendation
Today, the trust has turned into one of the most beneficial solutions to improve recommender systems, especially in the collaborative filtering method. However, trust statements suffer from a number of shortcomings, including the trust statements sparsity, users' inability to express explicit trust for other users in most of the existing applications, etc. Thus to overcome these problems, this ...
متن کاملA New Similarity Measure Based on Item Proximity and Closeness for Collaborative Filtering Recommendation
Recommender systems utilize information retrieval and machine learning techniques for filtering information and can predict whether a user would like an unseen item. User similarity measurement plays an important role in collaborative filtering based recommender systems. In order to improve accuracy of traditional user based collaborative filtering techniques under new user cold-start problem a...
متن کاملDetecting frauds using customer behavior trend analysis and known scenarios
In this paper a fraud detection method is proposed which user behaviors are modeled using two main components namely the un-normal trend analysis component and scenario based component. The extent of deviation of a transaction from his/her normal behavior is estimated using fuzzy membership functions. The results of applying all membership functions on a transaction will then be infused and a f...
متن کاملA NOVEL FUZZY-BASED SIMILARITY MEASURE FOR COLLABORATIVE FILTERING TO ALLEVIATE THE SPARSITY PROBLEM
Memory-based collaborative filtering is the most popular approach to build recommender systems. Despite its success in many applications, it still suffers from several major limitations, including data sparsity. Sparse data affect the quality of the user similarity measurement and consequently the quality of the recommender system. In this paper, we propose a novel user similarity measure based...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014