/Hotel-Reviews-Sentiment-Analyser-Using-StanfordCoreNLP

Sample code demonstrating the use of stanford's CoreNLP to analyse sentiments of hotel reviews using the Restaurant reviews dataset from Kaggle.

Primary LanguageJavaApache License 2.0Apache-2.0

Hotel Reviews Sentiment Analyser

Hotel review sentiment Analyser is an NLP project that rates the reviews based on sentiment classification using stanford's CoreNLP.

data

Hotel review sentiment Analyser uses restaurant review dataset from Kaggle [https://www.kaggle.com/c/restaurant-reviews/data] filename : 1-restaurant-test.csv

models

Hotel review sentiment Analyser utilizes : SentimentAnalysisCoreNLP.java: Recursive Neural Tensor Network via [Stanford CoreNLP] (http://nlp.stanford.edu/sentiment/code.html) for sentiment analysis.

Academic Background

Dataset: Restaurant reviews from Kaggle : https://www.kaggle.com/c/restaurant-reviews/data Recursive Neural Tensor Network: [Socher et al. 2013] (http://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf)

Software Dependencies

Hotel review sentiment Analyser is written in Java 8 and uses library Stanford CoreNLP. The project uses Maven as build tool.

License

This project uses the [Apache 2.0 License] : https://github.com/aima-adv/hotel_review_sentimentAnalyser/blob/master/LICENSE