Movie Review Dataset Research Articles

Disquisition of Sentiment Inquiry with Hashing and Counting Vectorizer using Machine Learning Classification

With the rapid growth in technology, analysis of feedback and reviews by the customers in companies and industries becomes a major challenge. The profit of the company mainly depends on the customer satisfaction. The view of the customer can be analyzed only through feedback. The review analysis can be utilized for the prediction of current sales and future sales of the company. With this overview, the paper aims in performing the sentiment analysis of the movie review. The Type of comment given by the customer is predicted and categorized into classes. The sentiment Analysis on movie Review dataset taken from the KAGGLE leading Dataset repository is used for implementation. The categorization of sentiment classes is achieved in five categories. Firstly, the target count for each sentiment is portrayed. The Resampling is done for equalizing the target sentiment count. Secondly, the extraction of sentiment feature words for each target is displayed and the data cleaning is done with Term Frequency Inverse document Frequency method. Thirdly, the resampled dataset is then fitted with the various classifiers like Multinomial Naives Bayes Classifier, Logistic Regression Classifier, KNearest Neighbors Classifier, Bernoulli Naives Bayes Classifier, Complement Naives Bayes Classifier, Nearest Centroid Classifer, Passive Aggressive Classifier, SGD Classifier, Ridge Classifier, Perceptron Classifier. Fourth, the feature extraction is done with Hashing Vectorizer and Counting Vectorizer. The vocabulary features are also displayed from the dataset. Fifth, the Performance analysis of clasifier is done with metrics like Accuracy, Recall, FScore and Precision. The implementation is carried out using python code in Spyder Anaconda Navigator IP Console. Experimental results shows that the sentiment prediction and classification done by Ridge classifier is found to be effective with Precision of 0.89, Recall of 0.88, FScore of 0.87 and Accuracy of 89%.

Classification of Sentiment Based on Movie Feedback Given By Audiences

The need for generating automated sentiment on audience feedbacks has been the need of the hour. Manually going through the entire movie feedback becomes tedious therefore an attempt to predict the polarity of a movie based on the reviews using machine learning models is done. Usage of the IMDB movie reviews dataset has been done for training and testing. In this study we also try to depict the real-life problems of class imbalance and train-test splits, hence obtaining solutions for the same. The problem of class imbalance in today’s world has affected a large amount of predictive applications such as cancer detection , fraudulent transactions in banks etc, hence this study is an attempt to perform a solution to solve the class imbalance problem. Use of the undersampling method has been done in this study to improve the accuracy of an imbalanced class. Feature extraction methods such as Bag of Words and Term Frequency Inverse document Frequency have been used to generate features from the reviews. The Logistic regression and SVM classifiers have been used in the study to measure the accuracy. Along with the accuracy the Confusion Matrix has also been calculated to showcase the class imbalance taking its effect on the accuracy.

Sentiment Analysis Using Lstm

Extracting the sentiment of the text using machine learning techniques like LSTM is our area of concern. Classifying the movie reviews using LSTM is our problem statement. The reviews dataset is taken from the IMDB movie review dataset. Here we will classify a review based on the memory in the neural network of a LSTM cell state. Movie reviews often contain sensible content which describe the movie. We can manually decide whether a movie is good or bad by going through these reviews. Using machine learning approach we are classifying the movie reviews such that we can say that a movie is good or bad. LSTM is effective than many other techniques like RNN and CNN.

Predicting Sentiment Polarity of Microblogs using an LSTM – CNN Deep Learning Model

In this paper we propose a novel supervised machine learning model to predict the polarity of sentiments expressed in microblogs. The proposed model has a stacked neural network structure consisting of Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) layers. In order to capture the long-term dependencies of sentiments in the text ordering of a microblog, the proposed model employs an LSTM layer. The encodings produced by the LSTM layer are then fed to a CNN layer, which generates localized patterns of higher accuracy. These patterns are capable of capturing both local and global long-term dependences in the text of the microblogs. It was observed that the proposed model performs better and gives improved prediction accuracy when compared to semantic, machine learning and deep neural network approaches such as SVM, CNN, LSTM, CNN-LSTM, etc. This paper utilizes the benchmark Stanford Large Movie Review dataset to show the significance of the new approach. The prediction accuracy of the proposed approach is comparable to other state-of-art approaches.

Investigating Machine Learning Techniques for User Sentiment Analysis

Sentiment analysis identifies users in the textual reviews available in social networking sites, tweets, blog posts, forums, status updates to share their emotions or reviews and these reviews are to be used by market researchers to do know the product reviews and current trends in the market. The sentiment analysis is performed by two methods. Machine learning approaches and lexicon methods which are also known as the knowledge base approach. These. In this article, the authors evaluate the performance of some machine learning techniques: Maximum Entropy, Naïve Bayes and Support Vector Machines on two benchmark datasets: the positive-negative dataset and a Movie Review dataset by measuring parameters like accuracy, precision, recall and F-score. In this article, the authors present the performance of various sentiment analysis and classification methods by classifying the reviews in binary classes as positive, negative opinion about reviews on different domains of dataset. It is also justified that sentiment analysis using the Support Vector Machine outperforms other machine learning techniques.

A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis

Nowadays, social media has become a tremendous source of acquiring user’s opinions. With the advancement of technology and sophistication of the internet, a huge amount of data is generated from various sources like social blogs, websites, etc. In recent times, the blogs and websites are the real-time means of gathering product reviews. However, excessive number of blogs on the cloud has enabled the generation of huge volume of information in different forms like attitudes, opinions, and reviews. Therefore, a dire need emerges to find a method to extract meaningful information from big data, classify it into different categories and predict end user’s behaviors or sentiments. Long Short-Term Memory (LSTM) model and Convolutional Neural Network (CNN) model have been applied to different Natural Language Processing (NLP) tasks with remarkable and effective results. The CNN model efficiently extracts higher level features using convolutional layers and max-pooling layers. The LSTM model is capable to capture long-term dependencies between word sequences. In this study, we propose a hybrid model using LSTM and very deep CNN model named as Hybrid CNN-LSTM Model to overcome the sentiment analysis problem. First, we use Word to Vector (Word2Vc) approach to train initial word embeddings. The Word2Vc translates the text strings into a vector of numeric values, computes distance between words, and makes groups of similar words based on their meanings. Afterword embedding is performed in which the proposed model combines set of features that are extracted by convolution and global max-pooling layers with long term dependencies. The proposed model also uses dropout technology, normalization and a rectified linear unit for accuracy improvement. Our results show that the proposed Hybrid CNN-LSTM Model outperforms traditional deep learning and machine learning techniques in terms of precision, recall, f-measure, and accuracy. Our approach achieved competitive results using state-of-the-art techniques on the IMDB movie review dataset and Amazon movie reviews dataset.

Short Text Classification Improved by Feature Space Extension

With the explosive development of mobile Internet, short text has been applied extensively. The difference between classifying short text and long documents is that short text is of shortness and sparsity. Thus, it is challenging to deal with short text classification owing to its less semantic information. In this paper, we propose a novel topic-based convolutional neural network (TB-CNN) based on Latent Dirichlet Allocation (LDA) model and convolutional neural network. Comparing to traditional CNN methods, TB-CNN generates topic words with LDA model to reduce the sparseness and combines the embedding vectors of topic words and input words to extend feature space of short text. The validation results on IMDB movie review dataset show the improvement and effectiveness of TB-CNN.

A Backdoor Attack Against LSTM-Based Text Classification Systems

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been reported to be a new type of threat. In this attack, the adversary will inject backdoors into the model and then cause the misbehavior of the model through inputs including backdoor triggers. Existed research mainly focuses on backdoor attacks in image classification based on CNN, little attention has been paid to the backdoor attacks in RNN. In this paper, we implement a backdoor attack against LSTM-based text classification by data poisoning. After the backdoor is injected, the model will misclassify any text samples that contains a specific trigger sentence into the target category determined by the adversary. The backdoor attack is stealthy and the backdoor injected in the model has little impact on the performance of the model. We consider the backdoor attack in black-box setting, where the adversary has no knowledge of model structures or training algorithms except for a small amount of training data. We verify the attack through sentiment analysis experiment on the dataset of IMDB movie reviews. The experimental results indicate that our attack can achieve around 96% success rate with 1% poisoning rate.

Enhancement of SentiWordNet using contextual valence shifters

Sentence structure has a considerable impact on the sentiment polarity of a sentence. In the presence of contextual valence shifters like conjunctions, conditionals and intensifiers some parts of the sentence are more relevant to determine the sentence polarity. In this work we have used valence shifters in sentences to enhance the sentiment lexicon SentiWordNet in a given document set. They have also been used to improve the sentiment analysis at document level. In the near past, micro blogging services like Twitter have become an important data source for sentiment analysis. Tweets, being restricted to 140 characters have slangs, are grammatically incorrect, have spelling mistakes and have informal expressions. The method is aimed at noisy and unstructured data like tweets on which computationally intensive tools like dependency parsers are not very successful. Our proposed system works better on both noisy (Stanford and airlines datasets of Twitter) and structured (movie review) datasets.

Opinion Mining: An Approach to Feature Engineering

Sentiment Analysis or opinion mining refers to a process of identifying and categorizing the subjective information in source materials using natural language processing (NLP), text analytics and statistical linguistics. The main purpose of opinion mining is to determine the writer’s attitude towards a particular topic under discussion. This is done by identifying a polarity of a particular text paragraph using different feature sets. Feature engineering in pre-processing phase plays a vital role in improving the performance of a classifier. In this paper we empirically evaluated various features weighting mechanisms against the well-established classification techniques for opinion mining, i.e. Naive Bayes-Multinomial for binary polarity cases and SVM-LIN for multiclass cases. In order to evaluates these classification techniques we use Rotten Tomatoes publically available movie reviews dataset for training the classifiers as this is widely used dataset by research community for the same purpose. The empirical experiment concludes that the feature set containing noun, verb, adverb and adjective lemmas with feature-frequency (FF) function perform better among all other feature settings with 84% and 85% correctly classified test instances for Naïve Bayes and SVM, respectively.

A novel sentiment classification model based on online learning

Memory limitation and slow training speed are two important problems in sentiment analysis. In this paper, we propose a sentiment classification model based on online learning to improve the training speed of the sentiment classification. First, combining the adaptive adjustment of learning rate of the Adadelta algorithm and the characteristics of avoid frequent jitter of Adam algorithm in the later stage of training, we present a novel Adamdelta algorithm. It solves the problem that learning rate of traditional follow the regularized leader (FTRL)-Proximal online learning algorithm will disappear with the increase of training times. Moreover, we gain an optimized logistic regression (LR) model and use it to the sentiment classification of online learning. Finally, we compare the proposed algorithm with five similar models with the experimental data of the IMDb movie review dataset. Experimental results show that the improved algorithm has better classification effect and can effectively improve the precision and recall of the classifier.

Taste Transitivity for Collaborative Filtering: A Stochastic Network Dynamics Approach

ABSTRACTWe develop a stochastic actor‐based network model for online movie reviews and analyze social network dynamics to study the user‐movie taste networks constructed from real movie review datasets. Examining such taste networks provides useful insights into factors underlying the performance of collaborative filtering‐based recommenders. Our results show that similar taste transitivity effect does exist that support collaborative filtering methods to recommend movies based on user taste similarity. We also investigate the role of movie popularity, genre, user gender, age, and geographic location in the taste network evolution. The findings provide insights to improve current movie recommendation systems. The two‐ mode network analyses approach taken in this article will also be broadly useful in obtaining better understanding of factors that drive user appreciations for varied products.

An ensemble approach to stabilize the features for multi-domain sentiment analysis using supervised machine learning

Sentiment classification or sentiment analysis has been acknowledged as an open research domain. In recent years, an enormous research work is being performed in these fields by applying numerous methodologies. Feature generation and selection are consequent for text mining as the high dimensional feature set can affect the performance of sentiment analysis. This paper investigates the inability of the widely used feature selection method (IG, Chi Square, Gini Index) individually as well as their combined approach on four machine learning classification algorithm. The proposed methods are evaluated on three standard datasets viz. IMDb movie review, electronics and kitchen product review dataset. Initially, select the feature subsets from three different feature selection methods. Thereafter, statistical method UNION, INTERSECTION and revised UNION method are applied to merge these different feature subsets to obtain all top ranked including common selected features. Finally, train the classifier SMO, MNB, RF, and LR (logistic regression) with this feature vector for classification of the review data set. The performance of the algorithm is measured by evaluation methods such as precision, recall, F-measure and ROC curve. Experimental results show that the combined method achieved best accuracy of 92.31 with classifier SMO, which is encouraging and comparable to the related research.

How textual quality of online reviews affect classification performance: a case of deep learning sentiment analysis

Cognitive computing is an interdisciplinary research field that simulates human thought processes in a computerized model. One application for cognitive computing is sentiment analysis on online reviews, which reflects opinions and attitudes toward products and services experienced by consumers. A high level of classification performance facilitates decision making for both consumers and firms. However, while much effort has been made to propose advanced classification algorithms to improve the performance, the importance of the textual quality of the data has been ignored. This research explores the impact of two influential textual features, namely the word count and review readability, on the performance of sentiment classification. We apply three representative deep learning techniques, namely SRN, LSTM, and CNN, to sentiment analysis tasks on a benchmark movie reviews dataset. Multiple regression models are further employed for statistical analysis. Our findings show that the dataset with reviews having a short length and high readability could achieve the best performance compared with any other combinations of the levels of word count and readability and that controlling the review length is more effective for garnering a higher level of accuracy than increasing the readability. Based on these findings, a practical application, i.e., a text evaluator or a website plug-in for text evaluation, can be developed to provide a service of review editorials and quality control for crowd-sourced review websites. These findings greatly contribute to generating more valuable reviews with high textual quality to better serve sentiment analysis and decision making.

Learning Representations of Natural Language Texts with Generative Adversarial Networks at Document, Sentence, and Aspect Level

The ability to learn robust, resizable feature representations from unlabeled data has potential applications in a wide variety of machine learning tasks. One way to create such representations is to train deep generative models that can learn to capture the complex distribution of real-world data. Generative adversarial network (GAN) approaches have shown impressive results in producing generative models of images, but relatively little work has been done on evaluating the performance of these methods for the learning representation of natural language, both in supervised and unsupervised settings at the document, sentence, and aspect level. Extensive research validation experiments were performed by leveraging the 20 Newsgroups corpus, the Movie Review (MR) Dataset, and the Finegrained Sentiment Dataset (FSD). Our experimental analysis suggests that GANs can successfully learn representations of natural language texts at all three aforementioned levels.

Deep Learning Based Sentiment Analysis Using Convolution Neural Network

Sentiment analysis (SA) of natural language text is an important and challenging task for many applications of Natural Language Processing. Till now, researchers have used different types of SA techniques such as lexicon based and machine learning to perform SA for different languages such as English, Chinese. Inspired by the gain in popularity of deep learning models, we conducted experiments using different configuration settings of convolutional neural network (CNN) and performed SA of Hindi movie reviews collected from online newspapers and Web sites. The dataset has been manually annotated by three native speakers of Hindi to prepare it for training of the model. The experiments are conducted using different numbers of convolution layers with varying number and size of filters. The CNN models are trained on 50% of the dataset and tested on remaining 50% of the dataset. For the movie reviews dataset, the results given by our CNN model are compared with traditional ML algorithms and state-of-the-art results. It has been observed that our model is able to achieve better performance than traditional ML approaches and it has achieved an accuracy of 95%.

Sentiment Analysis: Comparative Study between GSVM and KNN

Sentiment classification aims detecting general opinion of users in social media towards business products or daily life events. The classification tells whether sentiment is positive or negative. Techniques of sentiment classification are categorized into lexical analysis and machine learning techniques. In this paper, we propose a comparative study between SVM applied genetics (GSVM) against KNN algorithm in terms of speed and accuracy. We present also an experimental study of sentiment classification on different domains movie reviews, financial and amazon toys products. The experimental results shows that GSVM achieves a classification accuracy of 92% and KNN achieves 87% on movie reviews dataset. For classification speed, KNN shows a remarkable improvement (above 10% improvement) in comparison with GSVM.

Semi-Supervised Learning From Crowds Using Deep Generative Models

Although supervised learning requires a labeled dataset, obtaining labels from experts is generally expensive. For this reason, crowdsourcing services are attracting attention in the field of machine learning as a way to collect labels at relatively low cost. However, the labels obtained by crowdsourcing, i.e., from non-expert workers, are often noisy. A number of methods have thus been devised for inferring true labels, and several methods have been proposed for learning classifiers directly from crowdsourced labels, referred to as "learning from crowds." A more practical problem is learning from crowdsourced labeled data and unlabeled data, i.e., "semi-supervised learning from crowds." This paper presents a novel generative model of the labeling process in crowdsourcing. It leverages unlabeled data effectively by introducing latent features and a data distribution. Because the data distribution can be complicated, we use a deep neural network for the data distribution. Therefore, our model can be regarded as a kind of deep generative model. The problems caused by the intractability of latent variable posteriors is solved by introducing an inference model. The experiments show that it outperforms four existing models, including a baseline model, on the MNIST dataset with simulated workers and the Rotten Tomatoes movie review dataset with Amazon Mechanical Turk workers.

Comparative study of deep learning models for sentiment analysis

Sentiment analysis is one of the new absorbing parts appeared in natural language processing with the emergence of community sites on the web. Taking advantage of the amount of information now available, research and industry have been seeking ways to automatically analyze the sentiments expressed in texts. The challenge for this task is the human language ambiguity, and also the lack of labeled data. In order to solve this issue, sentiment analysis and deep learning have been merged as deep learning models are effective due to their automatic learning capability. In this paper, we provide a comparative study on IMDB movie review dataset, we compare word embeddings and further deep learning models on sentiment analysis and give broad empirical outcomes for those keen on taking advantage of deep learning for sentiment analysis in real-world settings.

Sentiment classification with word localization based on weakly supervised learning with a convolutional neural network

In order to maximize the applicability of sentiment analysis results, it is necessary to not only classify the overall sentiment (positive/negative) of a given document but also to identify the main words that contribute to the classification. However, most datasets for sentiment analysis only have the sentiment label for each document or sentence. In other words, there is a lack of information about which words play an important role in sentiment classification. In this paper, we propose a method for identifying key words discriminating positive and negative sentences by using a weakly supervised learning method based on a convolutional neural network (CNN). In our model, each word is represented as a continuous-valued vector and each sentence is represented as a matrix whose rows correspond to the word vector used in the sentence. Then, the CNN model is trained using these sentence matrices as inputs and the sentiment labels as the output. Once the CNN model is trained, we implement the word attention mechanism that identifies high-contributing words to classification results with a class activation map, using the weights from the fully connected layer at the end of the learned CNN model. To verify the proposed methodology, we evaluated the classification accuracy and the rate of polarity words among high scoring words using two movie review datasets. Experimental results show that the proposed model can not only correctly classify the sentence polarity but also successfully identify the corresponding words with high polarity scores.