Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476271Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Saidah Saad, Dr. | |
| dc.contributor.author | Ali Sabah Abdulameer (P72235) | |
| dc.date.accessioned | 2023-10-06T09:15:36Z | - |
| dc.date.available | 2023-10-06T09:15:36Z | - |
| dc.date.issued | 2015-08-01 | |
| dc.identifier.other | ukmvital:80509 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476271 | - |
| dc.description | The amount of information have been increasing tremendously especially with the use of the social media applications such Twitter, Facebook and YouTube. Twitter is a common social application which enables users to share their current thoughts and actions, comment on breaking news and engage in discussions. Trends are typically driven by emerging events, breaking news and general topics that attract the attention of a large fraction of Twitter users. Trend detection is thus of high value to news reporters and analysts, as they might point to fast-evolving news stories. Trend detection of events is important to companies, governments, national security agencies, journalists to develop strategies to remedy them. Researcher have been trying to detect trends by using machine learning techniques such as clustering based method in major languages such as English, German, and French while Arabic language is still in its infancy. The Arab world has been contributing to a huge amount of data due to big events that have been occurring in the Middle East. The aim of this research to is detect trends in the arabic social media. However, this research need to overcome several issues such as processing of the Arabic user generated content and lack of resources. In order to solve these issues, this research presents a voting combination clustering approach which is divided into six phases which are dataset collection from Twitter, text pre-processing, spam filtering by using Naive Bayes, feature selection based on Term Frequency Inverse Document Frequency and Entropy, statistical analyses and evaluation. Three statistical approaches are used which are Co-occurence, K-means and voting combination clustering. The analysis was performed in order to classify the trends into three categories which are Arabic nationality events, personal events and other events. The experimental results showed that the voting combination clustering achieved 93%, 87% and 90% for precision, recall and f-measure in trend detection respectively.,Master of Computer Science | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Data mining | |
| dc.subject | Information retrieval | |
| dc.subject | Machine learning | |
| dc.subject | Online social networks | |
| dc.subject | Universiti Kebangsaan Malaysia -- Dissertations | |
| dc.subject | Dissertations, Academic -- Malaysia | |
| dc.title | Trend detection in the Arabic social media using voting combination | |
| dc.type | theses | |
| dc.format.pages | 81 | |
| dc.identifier.callno | QA76.9.D343A236 2015 3 tesis | |
| dc.identifier.barcode | 002076 (2016) | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_80509+SOURCE1+SOURCE1.0.PDF Restricted Access | 290.8 kB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.