Social networks event mining framework for peacebuilding application /
Peace provides the freedom to express our views, to relate with other people, to create cooperation facilities, whereas social networks (SNs) provide a platform to do so. SNs can play a significant role in improving peacebuilding (Pb) process as recent peace-related studies witness that, peace and c...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,
2017
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Peace provides the freedom to express our views, to relate with other people, to create cooperation facilities, whereas social networks (SNs) provide a platform to do so. SNs can play a significant role in improving peacebuilding (Pb) process as recent peace-related studies witness that, peace and crisis reports are communicated by different SNs. People and victims of crisis usually utilize SNs and its applications to transmit their feelings. However, the most important setback of these SNs is to maintain the enormous amount of SNs data and to extract topic specific information. There is a lack of sufficient research on Pb process using social network event mining (SNEM) approach. Therefore, the objective of this research is to propose a framework, design and implement the framework; to extract peace related events from the oceanic data of SNs; to analyze user sentiments about that event and to cluster events further into sub-event. The framework is based on three proposed algorithms 1) data extraction and emerging event detection algorithm; 2) sentiment analysis (SA) algorithm; and 3) Clustering and tag cloud algorithm. To implement the proposed framework, this research has come up with the algorithms, that has been transformed into an application; named as TEMiner. This research has automatically extracted the specific Pb events (tweets) from millions of tweets posted per day, processed the sentiments of users about the events and cluster data based on identified events using TEMiner application. Furthermore, visualization techniques have been used for representing the results from different perspective and to provide user friendly graphical user interface that helps in quick analysis of the results. Thus, experimental results have proven that the proposed framework is viable to apply in extracting real time events, clustering them into sub-events, and analyzing user sentiments based on the extracted specific event, topic, or product. |
|---|---|
| Physical Description: | xvi, 122 leaves : illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 96-103). |