Description
ABSTRACT
This paper proposes a system enforcing content-based message filtering conceived as a key service for Social Networks (OSNs). The system allows OSN users to have a direct control on the messages posted on their walls.
This is achieved through a flexible rule-based system, that allows a user to customize the filtering criteria to be applied to their walls, and a Machine Learning based soft classifier automatically producing membership labels in support of content-based filtering.
TABLE OF CONTENT
COVER PAGE
APPROVAL PAGE
DEDICATION
ACKNOWLEDGEMENT
TABLE OF CONTENT
- INTRODUCTION
- BACKGROUND OF THE PROJECT
- AIM OF THE PROJECT
- SCOPE OF STUDY
- PROJECT ORGANISATION
CHAPTER TWO
2.0 LITERATURE REVIEW
2.1 BASICS OF SOCIAL MEDIA AND DEEP LEARNING
2.2 CONCEPTS SOCIAL MEDIA AND DEEP LEARNING
2.3 TYPES OF SOCIAL MEDIA
2.4 TERMINOLOGIE OF SOCIAL MEDIA AND DEEP LEARNING
2.5 CONCEPTIONAL VIEW OF THE STUDY
2.6 DEEP LEARNING IN SOCIAL MEDIA
2.7 REVIEW OF RELATED STUDIES
2.8 RECOMMENDATION USING DL
CHAPTER THREE
3.0 METHODOLOGY
3.1 DATA COLLECTION
3.2 HUMAN ANNOTATIONS
3.3 REAL-TIME FILTERING OF IMAGES
3.4 RELEVANCY FILTERING
3.5 DE-DUPLICATION FILTERING
CHAPTER FOUR
4.1 EXPERIMENTAL FRAMEWORK
4.2 DISCUSSION
CHAPTER FIVE
5.1 CONCLUSION
5.4 BIBLIOGRAPHY
CHAPTER ONE
1.0 INTRODUCTION
1.1 BACKGROUND OF THE PROJECT
In the last years, On-line Social Networks (OSNs) such as twitter and facebook have become a popular interactive medium to communicate, share and disseminate a considerable amount of human life information. Daily and continuous communication implies the exchange of several types of content, including free text, image, audio and video data. The huge and dynamic character of these data creates the premise for the employment of web content mining strategies aimed to automatically discover useful information dormant within the data and then provide an active support in complex and sophisticated tasks involved in social networking analysis and management. A main part of social network content is constituted by short text, a notable example are the messages permanently written by OSN users on particular public/private areas, called in general walls.
The aim of the present work is to propose and experimentally evaluate an automated system, called Filtered Wall (FW), able to filter out unwanted messages from social network user walls. The key idea of the proposed system is the support for content-based user preferences. This is possible thank to the use of a Machine Learning (ML) text categorization procedure [21] able to automatically assign with each message a set of categories based on its content. We believe that the proposed strategy is a key service for social networks in that in today social networks users have little control on the messages displayed on their walls. For example, Facebook allows users to state who is allowed to insert messages in their walls (i.e., friends, friends of friends, or defined groups of friends). However, no content-based preferences are supported. For instance, it is not possible to prevent political or vulgar messages. In contrast, by means of the proposed mechanism, a user can specify what contents should not be displayed on his/her wall, by specifying a set of filtering rules. Filtering rules are very flexible in terms of the filtering requirements they can support, in that they allow to specify filtering conditions based on user profiles, user relationships as well as the output of the ML categorization process. In addition, the system provides the support for user-defined blacklist management, that is, list of users that are temporarily prevented to post messages on a user wall.
1.2 AIM OF THE PROJECT
The aim of the present work is to propose and experimentally evaluate an automated system, called Filtered Wall (FW), able to filter out unwanted messages from social network user walls.
1.3 SCOPE OF THE PROJECT
Deep learning (DL) has attracted increasing attention on account of its significant processing power in tasks, such as speech, image, or text processing. In order to the exponential development and widespread availability of digital social media (SM), analyzing these data using traditional tools and technologies is tough or even intractable. DL is found as an appropriate solution to this problem. In this paper, we keenly discuss the practiced DL architectures by presenting a taxonomy-oriented summary, following the major efforts made toward the SM analytics (SMA). Nevertheless, instead of the technical description, this paper emphasis on describing the SMA-oriented problems with the DL-based solutions.
1.4 PROJECT ORGANISATION
The work is organized as follows: chapter one discuses the introductory part of the work, chapter two presents the literature review of the study, chapter three describes the methods applied, chapter four discusses the results of the work, chapter five summarizes the research outcomes and the recommendations.
Reviews
There are no reviews yet.