• Mohini Somvanshi
• Dr. D P Gaikwad

Sentiment analysis is the process of identifying and categorizing opinions expressed in the text, especially in order to determine whether the writer's attitude towards a particular topic, product, etc. is positive, negative, or neutral. Sentiment analysis is an effective solution to the concentrate on modeling user-generated review and overall rating pairs. The aim is to identify linguistics aspects and aspect-level sentiments from the review data similarly on predict overall sentiments of reviews. However, systems are not very accurate at the level for determining sentiment of separate sentences. To upset the issues in one go underneath at unified framework, we propose a totally unique probabilistic supervised joint side and sentiment model (SJASM). SJASM represents every review documents among the style of the opinion pairs, and would be possibly at a similar time model aspect terms and corresponding opinion words of the review for hidden side and sentiment detection. It conjointly leverages sentimental overall ratings, which comes frequently with on-line reviews, as supervising data, and would be possibly infer the linguistics aspects and aspect-level sentiments that are not only purposeful but collectively predictive of overall sentiments of reviews. Moreover, we collectively develop economical abstract thought methodology for the parameter estimation of SJASM supported folded gibbs sampling. We build the social network web site on its user post with attaching files, on its file topic name match with product name then recommend to user on e-commerce web site.

Sentiment analysis, aspect-based sentiment analysis, probabilistic topic model, supervised joint topic model.

"USER-LEVEL SENTIMENT ANALYSIS TECHNIQUE IN ONE GO ON SOCIAL NETWORK AND E-COMMERCE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 2, page no.785-787, February-2020, Available :http://www.jetir.org/papers/JETIR2002111.pdf

"USER-LEVEL SENTIMENT ANALYSIS TECHNIQUE IN ONE GO ON SOCIAL NETWORK AND E-COMMERCE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 2, page no. pp785-787, February-2020, Available at : http://www.jetir.org/papers/JETIR2002111.pdf