Online product reviews and community links have turn out to be the most widespread platform for sharing the product info, with vast quantities of reviews displayed every day. Automatically created product summaries help explorers in choosing best product. It analytically explores the effect of statistical and textual reviews on manufactured goods sales performance. This paper suggested a new multi-text summarization method for distinguishing the best top-most significant sentences of product reviews. Most of the earlier works on review summarization have mainly scrutinized content exploration, which disrespects grave features like writer reliability and conflicting sentiments. We examined above features and established a novel sentence with significance metric. The content and sentiment similitudes were utilized to define the relationship of two sentences. To categorize the top-most sentences, the k-clustering procedure was utilized to divide sentences towards k-groups. The final summarization sentence are selected from k-group. To calculate the efficiency of the suggested approach, we used product review from Amazon. The results show that the suggested method outpaces the other approach, it can provide more complete information about product. This study paper observes the business impression of product reviews. It analytically examines the effect of statistical and textual reviews on manufactured goods sales performance and to accepting their products and challengers’ products, which provide perceptions into their product development progress.
Sheela, J., & Janet, B. (2019). Context –sensitive sentimental based text summarization and classification based on the occurrence of trigger term in a sentence. International Journal of Engineering and Advanced Technology, 8(5), 1622–1626.