Development proposal report

On

Adaptive Depth of Mediation to Evaluate the Reliability of a System-Based Group Recommender and the Level of Trust between Different Users in a Collaborative Group Recommender

By

Abstract

In this research we try to explore the notion of system-based group recommendation in a holistic context. The main focus of the research is on adaptive depth of mediation that is employed in order to assess the reliability of this recommender system.

The research also analyzes many aspects of decision making process and tries to gauge its effect on the level of trust that exists between varying users in a collaborative group recommender system.

Finally the research attempts to evaluate two parts of the recommender system which can furnish recommendations to a group of users by deliberating their profiles and another system wherein a group of users can meet and share their recommendation.

Chapter1: Introduction

Proposal Outline

This research proposal concentrates on the several facets of group recommendation system and constitutes of the following chapters:

1.Introduction

2.Statement of Problem

3.Background Survey

4.Proposed Approach

5.Work Plan

Introduction

Recommender systems gather information employing collaborative filtering systems to find out users' tastes and concerns as they explore the Internet. Sites can gather information about an individual's personal interests, compare their information to other users with similar interests and make recommendations such as movies that they may enjoy, the next book they should read, etc.

Most of us Internet users have come across a Recommender System in one way or another. They help users navigating through large product assortments and making decisions in e-commerce scenarios. Probably the most prominent example is the book recommendation service of the e-tailer Amazon.com. (Jameson & Smyth 2007, 21-33).

Technically, Recommender Systems have their roots in different fields such as Information Retrieval, text classification or decision support systems. The tutorial will offer an introduction to the various basic strategies and techniques for building Recommender Systems and will discuss community-based, content based, and knowledge based as well as hybrid approaches and how the effectiveness of such systems can be determined. (Jameson & Smyth 2007, 21-33)

Group recommender systems bring in an altogether arrangement of fresh disputes for recommender systems exploration. The belief of giving a set up of testimonials that will meet the needs of a grouping of users, with potential contending concerns, is intriguing in itself. Additionally, one ought to be concerned about the method of combining and recording the preferences of a variety of users because they involve themselves in recommendation dialogs at the same time. Taking decisions is not always an easy task since people need to consider several alternatives before deciding their choices. Therefore, in the past, many recommender schemes have been formulated to help individual users in taking their decisions as in Amazon and other online shops.

Group recommendation, which makes recommendations to a group of users instead of individuals, has become increasingly important in both the workspace and people's social activities, such as brainstorming sessions for coworkers and social TV for family members or friends. Group recommendation is a challenging problem due to the dynamics of group ...