Grant: Discovery Grants Program - Individual
Université de Montréal
$25,000.00
Privacy issues in electronic commerce and e-learning
EF 2011-12
Résumé
Web personalization is an Internet technique for adapting websites to individuals. In general, it is based on the user profile, which summarizes what the website knows about the individual user. Unfortunately, this information is too often obtained without the user's knowledge or consent. In this research, I focus on a special class of web personalization technique, known as recommender systems, which have been used primarily in the context of electronic commerce. Recommender systems have also been used in the context of e-learning in order to help students choose programs and courses.
Recommender systems are very useful, but they typically come at a price: in order to operate, it would seem that they need to collect information on those who use them. It follows that most current recommender systems suffer from various privacy-protection vulnerabilities. In the case of electronic commerce, customers who wish to obtain accurate recommendations are often asked to reveal information that they may consider private. The potential abuses from unscrupulous merchants could result in a serious erosion of the customer's privacy, who should be able to keep private their personal information and not be tracked against their will.
In current e-learning systems: privacy concerns are nearly absent. Only primitive forms of privacy are offered in some platforms, such as not allowing the tutor any access to information about auto-evaluations performed by the learners. Nonetheless, the tutor has access to virtually all the remaining information including who are the students, what parts of the course they referred to, how many times and for how long, and all the information about the quizzes and tests the learner took in his course.
The main focus of the proposed research is to develop recommender systems capable of offering the electronic services that we have come to take for granted, but in ways that prevent the creation of user profiles that could be abused. The tutoring process itself, not only its recommendation, will also be studied from a privacy point of view. I shall use my dual expertise in electronic commerce and e-learning to cross-fertilize the two fields.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
183774-2008
Name nom
Aïmeur, Esma
Department département
Informatique et recherche opérationnelle
Organization id
63
Institution établissement
Université de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2008
Award amount
25000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Partie
4
Nb partie
5
Application title
Privacy issues in electronic commerce and e-learning
Keyword
NSERC
Application summary
Web personalization is an Internet technique for adapting websites to individuals. In general, it is based on the user profile, which summarizes what the website knows about the individual user. Unfortunately, this information is too often obtained without the user's knowledge or consent. In this research, I focus on a special class of web personalization technique, known as recommender systems, which have been used primarily in the context of electronic commerce. Recommender systems have also been used in the context of e-learning in order to help students choose programs and courses.
Recommender systems are very useful, but they typically come at a price: in order to operate, it would seem that they need to collect information on those who use them. It follows that most current recommender systems suffer from various privacy-protection vulnerabilities. In the case of electronic commerce, customers who wish to obtain accurate recommendations are often asked to reveal information that they may consider private. The potential abuses from unscrupulous merchants could result in a serious erosion of the customer's privacy, who should be able to keep private their personal information and not be tracked against their will.
In current e-learning systems: privacy concerns are nearly absent. Only primitive forms of privacy are offered in some platforms, such as not allowing the tutor any access to information about auto-evaluations performed by the learners. Nonetheless, the tutor has access to virtually all the remaining information including who are the students, what parts of the course they referred to, how many times and for how long, and all the information about the quizzes and tests the learner took in his course.
The main focus of the proposed research is to develop recommender systems capable of offering the electronic services that we have come to take for granted, but in ways that prevent the creation of user profiles that could be abused. The tutoring process itself, not only its recommendation, will also be studied from a privacy point of view. I shall use my dual expertise in electronic commerce and e-learning to cross-fertilize the two fields.