Detecting Spam Review through Sentiment Analysis

摘要: Online review can help people getting more information about store and product. The potential customers tend to make decision according it. However, driven by profit, spammers post spurious reviews mislead the promoting or demoting target store. Previous studies mainly utilize rating as indicator for detection. these ignore an important problem that will not necessarily represent sentiment accurately. In this paper, we first incorporate analysis techniques into spam proposed method compute score from natural language text a shallow dependency parser. We further discuss relationship between reviews. A series of discriminative rules are established through intuitive observation. end, paper establishes time combined with detect efficiently. Experimental results show methods in have good detection result outperform existing methods.