A proactive multi-type context-aware recommender system in the environment of internet of things

Dissertant

Salman, Yasamin A.

Thesis advisor

Abu Isa, Abd al-Latif

University

Birzeit University

Faculty

Faculty of Engineering and Technology

Department

Department of Computer Science

University Country

Palestine (West Bank)

Degree

Master

Degree Date

2016

English Abstract

In this age of information overload, people use a variety of strategies to make choices about what to buy, how to spend their leisure time, and even with whom to connect.

Recommender systems automate some of these strategies in order to predict user’s interest in information, products, and services among the tremendous amount of available items.

Recommender systems have been developed in parallel with the web.

Currently, these systems are incorporating context and social information of the user, producing context aware recommender systems.

In the future, they will use implicit, local and personal information of the user from the Internet of things.

The Internet of things paradigm encapsulates the concept of connectivity with anyone and anything at anytime and anywhere.

That’s why it will offer a lot of information about the user, thus knowing more about his context, and consequently enables high quality and satisfactory recommendations.

Most recommender systems follow the request-response approach.

This means that the recommendations are provided to the user upon his request.

Recently, a proactive recommender system - that pushes recommendations to the user when the current situation seems appropriate, without explicit user request - has been introduced in the research area of recommender systems.

In this thesis, a design of a context aware recommender system that recommends different types of items proactively in the Internet of things environment is proposed.

A major part of this design is the context aware management system which decides if the context is proper to push a recommendation or not, and what type of recommendations to push.

As a proof of concept of the proposed system, we have designed a three-type proactive recommender system.

The three types are: gas stations, restaurants and attractions.

We assume that the context aware management system inputs are derived virtually from the Internet of things, and its output is a score that determines if the context is appropriate for a recommendation and identifies the recommendation type.

In this context aware management system, we have used a neural network to do the reasoning of the context.

The results of 5000 random contexts were tested.

For an average of 98% of them, our trained neural network generated correct recommendation types in the correct times and contexts.

Moreover, A prototype for the system as an application has been developed and a user’s acceptance survey has been conducted to 50 users.

The results of the survey were very satisfactory and showed high users’ interest in such application.

Main Subjects

Information Technology and Computer Science

No. of Pages

85

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-728569