AN AUTOMATIC FRAMEWORK FOR DOCUMENT SPAM DETECTION USING ENHANCED CONTEXT FEATURE MATCHING
Main Article Content
Abstract
With the growth in the communication systems, opinions became the most used communication method in the corporates, research and education. Nevertheless, with the increasing popularity the challenge for all internet service providers is to keep matching the demand for bandwidth. The major challenge to keep the bandwidth up to the usage is dealing with the spam messages. A spam communication or review is something that the sender uses for promotion and for the received may be useless. Thus for the receiver the messages are mostly unimportant. The detection of the spam reviews cannot be done at the review server end and need to done at the receiver side. Failing in detecting the spam can easily overload the review communication channel and reduce the effective use of the bandwidth. A number of researchers are carried out in order to detect the spam messages by deploying the filters. The outcomes are partially satisfactory as most of the parallel researches have demonstrated the rejection of the documents based on the pre-defined keywords. Nonetheless, these methods are not satisfactory as the use of words for every review writer may vary. As a result influenced by certain keywords, the receiver may lose some important communications. Thus the demand of the modern research is to enhance the detection of the spam reviews by using enhanced techniques rather than only depending on the keywords. This work proposes a novel automated framework powered by machine learning technique to detect the keywords and improve the detection by deploying context detection methods. The major outcome of this work is to build and demonstrate an automated framework for review spam detection with review rejection filters. The work outcomes into a highly satisfactory detection rate and demonstrate a sustainable model.
Downloads
Download data is not yet available.
Article Details
Section
Articles
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.