Event detection based on on-line news clustering
The terrorist attack directly affects personal safety, and it also has a lasting impact on international politics, civil liberties, and the economy. Internet produces massive amounts of terrorist attack news every day, o how to extract news of interest is time-consuming work. In order to provide org...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/76044 |
| _version_ | 1826127775464947712 |
|---|---|
| author | Shi, Ke |
| author2 | Mao Kezhi |
| author_facet | Mao Kezhi Shi, Ke |
| author_sort | Shi, Ke |
| collection | NTU |
| description | The terrorist attack directly affects personal safety, and it also has a lasting impact on international politics, civil liberties, and the economy. Internet produces massive amounts of terrorist attack news every day, o how to extract news of interest is time-consuming work. In order to provide organized information to readers, clustering technology is used to automatically arrange vast news. In this project, a document representation model is trained by CNN and LSTM to represent each news as a 48-dimensional vector. Meanwhile, a hierarchical structure is designed to do the K-means and Affinity Propagation clustering. The first step is to cluster samples by locations, and the second step is to cluster samples by content information. As a result, the overall model obtains a satisfactory performance as Purity at 85.19%, RI at 82.12% and NMI at 76.42%. |
| first_indexed | 2024-10-01T07:14:21Z |
| format | Thesis |
| id | ntu-10356/76044 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:14:21Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/760442023-07-04T15:56:31Z Event detection based on on-line news clustering Shi, Ke Mao Kezhi School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering The terrorist attack directly affects personal safety, and it also has a lasting impact on international politics, civil liberties, and the economy. Internet produces massive amounts of terrorist attack news every day, o how to extract news of interest is time-consuming work. In order to provide organized information to readers, clustering technology is used to automatically arrange vast news. In this project, a document representation model is trained by CNN and LSTM to represent each news as a 48-dimensional vector. Meanwhile, a hierarchical structure is designed to do the K-means and Affinity Propagation clustering. The first step is to cluster samples by locations, and the second step is to cluster samples by content information. As a result, the overall model obtains a satisfactory performance as Purity at 85.19%, RI at 82.12% and NMI at 76.42%. Master of Science (Computer Control and Automation) 2018-09-24T11:59:38Z 2018-09-24T11:59:38Z 2018 Thesis http://hdl.handle.net/10356/76044 en 75 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Shi, Ke Event detection based on on-line news clustering |
| title | Event detection based on on-line news clustering |
| title_full | Event detection based on on-line news clustering |
| title_fullStr | Event detection based on on-line news clustering |
| title_full_unstemmed | Event detection based on on-line news clustering |
| title_short | Event detection based on on-line news clustering |
| title_sort | event detection based on on line news clustering |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/76044 |
| work_keys_str_mv | AT shike eventdetectionbasedononlinenewsclustering |