论文信息 - Classification of Sentiments from Movie Reviews Using KNIME

Classification of Sentiments from Movie Reviews Using KNIME

Nowadays in entertainment, cinema industry has become one of the most popular industries, gaining the attention of public toward them by making unnecessary stunts by the production team in promoting their movie and influencing the public to watch the movie at least for one time. By deeply understanding the impact of a particular movie in advance, using reviews made after watching the movie benefits others in saving the major resources like time and money. The objective of our research is to save the time and money spent on watching the movie in theaters and motivating them to use up their valuable time with family members, especially during weekends. In this paper, we aim to demonstrate the application on sentiment classification using decision tree algorithm available in KNIME to rate the movie performance. In which, the textual data from the document are converted into strings, and these strings are preprocessed to get numerical document vectors. Later, from the document vectors the sentiment class is extracted and the predicted model is built and evaluated. In our experimental work, 93.97% of classification accuracy with 0.863 Cohen’s value was achieved in classifying the sentiments from the movie reviews.

Syed Muzamil Basha | Dharmendra Singh Rajput | T. P. Thabitha | P. Srikanth | C. Pavan Kumar

[1] Bo Pang,et al. Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[2] John Blitzer,et al. Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[3] Christopher D. Manning,et al. Baselines and Bigrams: Simple, Good Sentiment and Topic Classification , 2012, ACL.

[4] Yoshua Bengio,et al. Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[5] Qiang Yang,et al. Cross-domain sentiment classification via spectral feature alignment , 2010, WWW '10.

[6] Thomas Hofmann,et al. Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification , 2017, WWW.

[7] Ting Liu,et al. Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[8] João Francisco Valiati,et al. Document-level sentiment classification: An empirical comparison between SVM and ANN , 2013, Expert Syst. Appl..

[9] Ronnie D. Caytiles,et al. Weighted Fuzzy Rule Based Sentiment Prediction Analysis on Tweets , 2017 .

[10] Santanu Kumar Rath,et al. Classification of sentiment reviews using n-gram machine learning approach , 2016, Expert Syst. Appl..

[11] Ming Zhou,et al. Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification , 2014, ACL.