Syed Muzamil Basha

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.

Fitting a Neural Network Classification Model in MATLAB and R for Tweeter Data set

Nowadays, the interest among the research community in sentiment analysis (SA) has grown exponentially. Our paper aims to find the prediction error occurred when we perform SA on tweets. The data set considered for the demonstration has 1129 tweets, and output parameters having predictor identifiers. Artificial neural networks (ANNs) are designed with ten hidden layers and one output layer. Additionally, trained the designed system with the help of MATLAB software to find the prediction error and also, derived sentiments using ggplot2 package in R.

Evaluating the Impact of Feature Selection on Overall Performance of Sentiment Analysis

Now a days the importance of analyzing the hidden sentiments from user reviews playing a prominent role towards increasing profitability in any organization. To address the challenges being faced in analyzing the text information and transforming the same in to polarities values with an objective of saving time in understanding the public opinion on particular product or service. Traditionally, there are different approaches carried out in transforming text data in to values based on different features of Text. In our research we make use of Stanford CoreNLP, Alias-is Lingpipe (uses Logistic regression for document classification), Senti WordNet and synthesize libraries from different sources to include several other techniques that are used for text mining to evaluate the impact of feature selection on overall sentiment analysis by scoring a sentences in a review using different scoring Techniques. we also included NTU Lib Linear to make use of linear SVM for document classification. The Features considered on our experiments are Term Frequency and N-Gram (1Gram & 2Gram) with Decision Tree as Prediction model to evaluate the Accuracy, Area under ROC Curve and Kappa value. Finally, Compared the polarities of the reviews obtained using three different sentiment scoring approaches. The findings in our research is, Term Frequency have good impact of (0.932) on classifying the sentiment, In contrast, 2Gram have an impact of (0.8505).