Bias detection based on text mining technique : a case study of western media coverage for Palestinian-Israeli conflict

Other Title(s)

كشف التحيز باستخدام تقنية تنقيب النصوص : دراسة حالة تغطية الإعلام الغربي للصراع الفلسطيني الإسرائيلي

Dissertant

Labad, Hibah Mahmud Ibrahim

Thesis advisor

al-Siraj, Wail Fikri

University

Islamic University

Faculty

Faculty of Information Technology

Department

Information Technology

University Country

Palestine (Gaza Strip)

Degree

Master

Degree Date

2018

English Abstract

The online mass media plays a critical role in influencing the public opinion about controversial political events.

Bias in press reports and articles to some ideological or political sides is common and opposites the neutrality nature of press and media.

Bias can take different aspects and ways.

One of the main aspects of press bias is using mislead terms and vocabularies.

In summer 2014, Western media, news and press agencies covered Israeli war on Gaza.

In general, Palestinian people complain that there is a notable bias in western media with the Israeli story and opinion and vice versa.

Finding political bias consider complicated process because of there a need for a specified taxonomy cover the political event.

In this master thesis; we report a text analytical experimental study, that’s have conducted on western media analysis to identify patterns in the press orientation and further in the media bias towards side to another.

We build three models different in their text level, which are Keywords, Quotes and Articles.

We have followed the text mining techniques and machine learning in an effort to detect the bias in news outlets.

We have crawled news articles form 14 major outlets in the western media.

Then we have made preprocessing to convert them into useful structured form, building s classifiers that be able to predict news outlets bias.

In addition, we have make a comparison between three of supervised machine learning algorithms behavior used in classification associated with different number of grams and stemmed attributes.

The three proposed models provide a distinguish behavior, but Articles Model have provided the most acceptable objective and subjective evaluation, its achieved 85.12% accuracy, 80.89% precision, 96.18% recall and f-measure 87.03%.

Main Topic

Media and Communication
Information Technology and Computer Science

Topics

No. of Pages

81

Table of Contents

Table of contents.

Abstract.

Abstract in Arabic.

Chapter One : Introduction.

Chapter Two : Literature review.

Chapter Three : Research methodology.

Chapter Four : Experiments.

Chapter Five : Results discussion.

Chapter Six : Evaluation and contributions.

Chapter Seven : Conclusion and future work.

References.

American Psychological Association (APA)

Labad, Hibah Mahmud Ibrahim. (2018). Bias detection based on text mining technique : a case study of western media coverage for Palestinian-Israeli conflict. (Master's theses Theses and Dissertations Master). Islamic University, Palestine (Gaza Strip)
https://search.emarefa.net/detail/BIM-905425

Modern Language Association (MLA)

Labad, Hibah Mahmud Ibrahim. Bias detection based on text mining technique : a case study of western media coverage for Palestinian-Israeli conflict. (Master's theses Theses and Dissertations Master). Islamic University. (2018).
https://search.emarefa.net/detail/BIM-905425

American Medical Association (AMA)

Labad, Hibah Mahmud Ibrahim. (2018). Bias detection based on text mining technique : a case study of western media coverage for Palestinian-Israeli conflict. (Master's theses Theses and Dissertations Master). Islamic University, Palestine (Gaza Strip)
https://search.emarefa.net/detail/BIM-905425

Language

English

Data Type

Arab Theses

Record ID

BIM-905425