Sentiment Analysis of Flipkart Product Reviews using Natural Language Processing
S Kiruthika1, U Sneha Dharshini2, K R Vaishnavi3, R V Vishwa Priya4
1S Kiruthika, Department of Computer Science and Engineering, Sri Krishna College of Technology, Coimbatore, (Tamil Nadu), India.
2U Sneha Dharshini, Department of Computer Science and Engineering, Sri Krishna College of Technology, Coimbatore, (Tamil Nadu), India.
3K R Vaishnavi, Department of Computer Science and Engineering, Sri Krishna College of Technology, Coimbatore, (Tamil Nadu), India.
4R V Vishwa Priya, Department of Computer Science and Engineering, Sri Krishna College of Technology, Coimbatore, (Tamil Nadu), India.
Manuscript received on 18 May 2023 | Revised Manuscript received on 29 May 2023 | Manuscript Accepted on 15 July 2023 | Manuscript published on 30 July 2023 | PP: 54-62 | Volume-12 Issue-2, July 2023 | Retrieval Number: 100.1/ijrte.B77740712223 | DOI: 10.35940/ijrte.B7774.0712223
Open Access | Editorial and Publishing Policies | Cite | Zenodo | 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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this contemporary world, people depend more on ecommerce sites or applications to purchase items on-line. People buy items online based on the scores and reviews provided by individuals who have previously purchased the same items, which helps identify the success or failure of the item. Furthermore, business suppliers or manufacturers assess the success or failure of their products by evaluating the reviews provided by clients. In the current system, several techniques have been utilised to determine a dataset of item evaluations. It also offered belief category formulas to utilise a monitored learning of the item reviews located in two different datasets. The proposed speculative methods examined the precision of all belief category formulas and ways to identify which formula is more precise. Additionally, the existing system is unable to detect fake favourable reviews and fake negative reviews using discovery procedures. One of the most popular works utilised “Bad” and “Outstanding” seed words to determine semantic positioning, while a factor brilliant shared information technique was employed to achieve this. The belief positioning of a file was defined as the typical semantic positioning of all such expressions. Semantic Positioning of contextindependent viewpoints is identified, and context-reliant viewpoints utilising linguistic guidelines to infer the positioning of context-specific perspectives are considered. Contextual information from various other reviews that discuss the same item function was extracted to identify the context-independent viewpoints.
Keywords: Semantic positioning, linguistic guidelines, context indistinct-dependent viewpoints.
Scope of the Article: Artificial Intelligence