Abstract
Online spamming has become a potential threat in the current digital world as most of the decisions made in daily life. Taking this as an advantage, businesses in various fields have either committing online spamming or being affected by the same for various reasons like market competition and profit gains. Even though there is a lot of research that’s been carried on identifying a single opinion as spam/no-spam. The huge gap left unbridged here is detecting the spamming activity in the business as a whole. Recent discoveries show that singleton review attack - technique where reviewers created multiple accounts and only write one review under each account is a significant source of spam reviews. For example approximately 68% of the amazon review data are singleton reviews. My research project is focused on detecting such businesses that are affected by opinion spamming activity over time. Extensive experiments showed our proposed models outperformed baseline methods in terms of precision, recall, and F1-score for identifying both honest and dishonest businesses.