REAL TIME VOICE REVIEW BASED AUDIO SENTIMENT ANALYSIS SYSTEM USING MULTI PERCEPTRON MODEL FOR E – COMMERCE
International Research Journal of Modernization in Engineering Technology and Science · 2024
Sentiment analysis is the automated process of tagging data according to their sentiment, such as positive, negative and neutral.Sentiment analysis allows companies to analyse data at scale, detect insights and automate processes.Thus, the ultimate goal of sentiment analysis is to decipher the underlying mood, emotion, or sentiment of a text.This is also known as Opinion Mining.Detecting sentiments is one of the most important marketing strategies in today's world.In the past, sentiment analysis used to be limited to researchers, machine learning engineers or data scientists with experience in natural language processing.Traditional sentiment analysis methods mainly rely on written texts such as reviews, feedback, surveys, etc.However, as human language is complex, nuances such as irony, sarcasm, or intentions are not always easily understood in the written content.The acoustic tone in audio files carries richer information and gives better insights into the sentiments.Normally sentiment analysis is done through the text data, but this project use audio data to detect a person's emotions just by their voice.Therefore, in this project develop an Audio Sentiment Analysis System for E-Commerce Website using voice reviews.The goal of this project is to proposes to build a Multi Perceptron model, LSTM model and CNN models.ASR converts speech into text, after which conventional text-based sentiment detection systems are applied.LSTM Model is used to recognize the sentiment and CNN model is used to classify the sentiments emotions i.e 1 = neutral, 2 = calm, 3 = happy, 4 = sad, 5 = angry, 6 = fearful, 7 = disgust, 8 = surprised.These decisions could improve business capacity, raise sales, enhance communication between a customer service agent and customer, and much more.Finding the sentiment of the customer helps in determining whether the customer was satisfied with the service or not.It can be very much useful to recommend products to customers based on their emotions towards that product.