Fake Review Identification Methods Based on Multidimensional Feature Engineering

<table class="table-group" id="tab5"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Feature item</td><td class="align_center">Threshold</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Length of reviews</td><td class="align_center">50</td></tr><tr><td class="align_left">Relativity of review content and products</td><td class="align_center">0.4</td></tr><tr><td class="align_left">Similarity of review content</td><td class="align_center">0.5</td></tr><tr><td class="align_left">Repetition ratio of words in reviews</td><td class="align_center">0.5</td></tr><tr><td class="align_left">Customers posting the maximum number of reviews in a day</td><td class="align_center">3</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Threshold values set for different features.</div>

Mobile Information Systems

tab5

Table 5

Table 5: Fake Review Identification Methods Based on Multidimensional Feature Engineering 