• RUHA JABEEN
• MD. ATEEQ UR RAHMAN

Utilizing on the web buyer audits as electronic informal exchange to help buy basic leadership has turned out to be increasingly famous. The Web gives a broad wellspring of shopper audits, although one can barely read all surveys to acquire a reasonable assessment of an item or administration. A content preparing system that can outline audits, would along these lines be alluring. A subtask to be rendred by such a system is locate the general angle classifications inclined to in audit sentences, for which this paper presents two strategies. As conflicting to most existing methodologies, the principal technique introduced is an unsupervised strategy that applies affiliation govern mining on co-event recurrence information acquired from a gist to discover these perspective classifications. While not competing with cutting edge directed strategies, the proposed unsupervised technique performs superior to a few straightforward baselines, a correlative yet regulated strategy, and a managed pattern, with a F1-score of 67%. The second technique is an administered variation that outflanks existing strategies with a F1-score of 84%.

Aspect Category Detection, Consumer Reviews, Co-Occurrence Data, Sentiment Analysis, Spreading Activation.

"Automated Feature Category Extraction for Sentiment Analysis Employing Natural Language Processing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.560-570, July-2018, Available :http://www.jetir.org/papers/JETIR1807808.pdf

"Automated Feature Category Extraction for Sentiment Analysis Employing Natural Language Processing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp560-570, July-2018, Available at : http://www.jetir.org/papers/JETIR1807808.pdf