Opinion spam detection using review and reviewer centric features

TLDR: This work will be implementing supervised learning to detect the spam in reviews using Hadoop architecture, and analysis and model building will be doing with the help of open source software H2O.

Abstract: Online reviews become one of the primary factors in many decision making situations. There is a possibility to impact the business negatively or positively. In this work, review centric features and the reviewer centric features will be considered for feature selection. Reviewer centric features give a comprehensive aspect of the reviews. These features will give the information about that particular author. Rather than information about the text content, review centric feature will give information about the reviews. One of the machine learning technique; supervised learning is used to detect the spam in reviews. This is implemented using Hadoop architecture. HDFS is used to store the data set. Analysis and model building will be doing with the help of open source software H2O.