Ml Based Naive Bayes Methodology for Rate Prediction Using Textual Rating and Find Actual or Movie Rating Based on Mbnbr Optimization
Hima Keerthi Penumetsa1, Shashi Mogalla2

1Hima Keerthi Penumetsa, Department of Computer Science and System Engineering, Andhra University, Vishakapatnam, India.
2Shashi Mogalla, Department of Computer Science and System Engineering, Andhra University, Vishakapatnam, India.

Manuscript received on 02 July 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 August 2019 | PP: 314-321 | Volume-8 Issue-10, August 2019 | Retrieval Number: I8232078919/2019©BEIESP | DOI: 10.35940/ijitee.I8232.0881019
Open Access | Ethics and  Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: We’ve experienced a bulk of review pages such as Amazon, Flip Kart & Facebook, book my show and some applications etc., in latest studies. It offers an excellent chance to share our reviews for different goods we buy. However, we are faced with the issue of duplicating data. It is essential where to stock precious data from feedback to comprehend the desires of a user and create a precise suggestion. Some variables, such as user buy documents, item type, and geographic place, are considered by conventional recommendation schemes. We suggest a Feeling Forecast Technique (FFT) in this job to enhance forecast precision in recommendation schemes. First, we suggest a personal assessment strategy for personal consumers and determine the feeling about objects/products of each customer. Second, we regard not only the own emotional characteristics of a customer but also the relational emotional impact. After which they count the credibility of the item that could be deduced from a consumer sets emotional scores reflecting the extensive assessment of clients. Finally, we combine in our recommendation scheme three elements feeling resemblance relational emotional, impact, and notoriety resemblance of item to create a precise forecast of rating. On an actual-world sample obtained from Glass door, we undertake a quality assessment of the three emotional variables. Our findings show that the feeling can well describe display settings that help improve the effectiveness of recommendations. Above all discussion is analyzed with ML based Naive Bayes optimization got 20% more efficiency compared to existed methods like linear regression, etc.
Keywords:  Naive Bayes Classifier, PD (Positive Dictionary), SDD (Sentiment Degree Dictionary), ND (Negation Dictionary), Social Media, move ML based naive Bayes rate prediction (MBNBR) OPTIMIZATION.
Scope of the Article: Waveform Optimization for Wireless Power Transfer