Rating consistency and review content based multiple stores review spam detection

Opinions and attitudes of others highly influence the human behavior and are central to almost all decision making activities which is known as the word-of-mouth effect in shaping decision making. Large amounts of online reviews, the valuable voice of the customer, benefit consumers and product designers. Posting reviews online has become an increasingly popular way for people to express opinions and sentiments towards the products bought or services received. Identifying and analyzing helpful reviews efficiently and accurately to satisfy both current and potential customer´s needs have become a critical challenge for market-driven product design. Hence, an efficient and effective Linguistic technique Sentiwordnet and a tool NLTK (Natural Language Tool Kit), Word Count and a method known as Counting method is proposed to find spamicity of the reviews based on the rating consistency and review content. The experimental results shows that the proposed technique has comparatively effective spamicity detection than other technique based on helpfulness votes (rating) and content of the reviews.