Skip to content

Aishwarya0898/Sentiment-Analysis

Repository files navigation

Sentiment-Analysis: Natural Laguage Processing CS733

We carried out this project in a team of three, instructed by Dr. Vikas at Old Dominion University. In this project, we aim to analyze the sentiment of customer reviews for breweries using text summarization techniques. Breweries often receive numerous reviews from customers, which can vary widely in length and content. By employing sentiment analysis and text summarization, we can extract key insights from these reviews more efficiently and effectively.

Methodology

Data Collection: We collect customer reviews from various online platforms such as Yelp, Google Reviews, and brewery-specific websites using Microsoft Power Automate Tool. The dataset includes text reviews along with associated metadata such as ratings, comments and dates.

Preprocessing: We preprocess the raw text data by removing noise such as punctuation, special characters, and stopwords. We also perform lemmatization or stemming to normalize the text.

Sentiment Analysis: We apply sentiment analysis techniques to determine the sentiment polarity (positive, negative, or neutral) of each review. This involves using pre-trained sentiment analysis models(BERT) or lexicons to classify the sentiment of the text.

Text Summarization: We use text summarization techniques to generate concise summaries of the reviews. This can involve extractive summarization, where key sentences or phrases are selected from the original text, or abstractive summarization, where new sentences are generated to capture the main ideas.

Integration: We integrate the sentiment analysis results with the text summarization to generate sentiment-aware summaries. This allows us to identify the overall sentiment expressed in the reviews while also highlighting the key aspects and opinions mentioned by customers.

Findings

Sentiment Distribution: We analyze the distribution of sentiment polarity across all reviews to understand the overall sentiment towards the breweries.

Key Themes: Through text summarization, we identify common themes and topics mentioned in the reviews such as beer quality, service, ambiance, and pricing.

Sentiment Trends: We examine how sentiment varies over time or across different breweries to identify patterns and trends.

Impact Analysis: We assess the impact of sentiment on various business metrics such as customer satisfaction, brand reputation, and financial performance.

Conclusion

Sentiment analysis combined with text summarization provides valuable insights into customer perceptions and opinions towards breweries. By summarizing and analyzing customer reviews, breweries can gain a better understanding of their strengths and weaknesses, identify areas for improvement, and make data-driven decisions to enhance customer satisfaction and loyalty.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published