Spam review detection (II)
Online opinions have become an essential part of decision making for millions of web users. However, in a pursuit of profit or success, imposters try to deceive people by opinion spamming to promote or demote a certain targets. The seriousness of the problem has attracted significant attention fro...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/55113 |
| _version_ | 1826121554074796032 |
|---|---|
| author | Tussupbekov, Yerken. |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Tussupbekov, Yerken. |
| author_sort | Tussupbekov, Yerken. |
| collection | NTU |
| description | Online opinions have become an essential part of decision making for millions of web users. However, in a pursuit of profit or success, imposters try to deceive people by opinion spamming to promote or demote a certain targets. The seriousness of the problem has attracted significant attention from different parties. Big companies develop new approaches of enhancing the filtering systems to detect spam, while spammers come up with new ways to disguise themselves.
In this paper, we study two major approaches for spam detection based on linguistic and behavioral features. While most of the past researches focused on either of the methods, in this work we combine the two together in an attempt to find the optimal spam filtering approach. We will take supervised learning approach, as the new ways of detecting training spam will be proposed and put to the test.
An in-depth investigation explores new principles for dataset construction that allows us to develop a classifier reaching remarkable 83.4% accuracy in spam filtering. Furthermore, additional enhancement to the developed system will be proposed, that could help to achieve even better performance. |
| first_indexed | 2024-10-01T05:34:06Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/55113 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:34:06Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/551132023-03-03T20:49:00Z Spam review detection (II) Tussupbekov, Yerken. School of Computer Engineering Zhang Jie DRNTU::Engineering::Computer science and engineering::Data::Coding and information theory Online opinions have become an essential part of decision making for millions of web users. However, in a pursuit of profit or success, imposters try to deceive people by opinion spamming to promote or demote a certain targets. The seriousness of the problem has attracted significant attention from different parties. Big companies develop new approaches of enhancing the filtering systems to detect spam, while spammers come up with new ways to disguise themselves. In this paper, we study two major approaches for spam detection based on linguistic and behavioral features. While most of the past researches focused on either of the methods, in this work we combine the two together in an attempt to find the optimal spam filtering approach. We will take supervised learning approach, as the new ways of detecting training spam will be proposed and put to the test. An in-depth investigation explores new principles for dataset construction that allows us to develop a classifier reaching remarkable 83.4% accuracy in spam filtering. Furthermore, additional enhancement to the developed system will be proposed, that could help to achieve even better performance. Bachelor of Engineering (Computer Science) 2013-12-12T08:48:05Z 2013-12-12T08:48:05Z 2013 2013 Final Year Project (FYP) http://hdl.handle.net/10356/55113 en Nanyang Technological University 38 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Data::Coding and information theory Tussupbekov, Yerken. Spam review detection (II) |
| title | Spam review detection (II) |
| title_full | Spam review detection (II) |
| title_fullStr | Spam review detection (II) |
| title_full_unstemmed | Spam review detection (II) |
| title_short | Spam review detection (II) |
| title_sort | spam review detection ii |
| topic | DRNTU::Engineering::Computer science and engineering::Data::Coding and information theory |
| url | http://hdl.handle.net/10356/55113 |
| work_keys_str_mv | AT tussupbekovyerken spamreviewdetectionii |