Search

Opinion summarization recapitulates the opinions about a common topic automatically. The primary motive of summarization is to preserve the properties of the text and is shortened in a way with no loss in the semantics of the text. The need of automatic summarization efficiently resulted in increased interest among communities of Natural Language Processing and Text Mining. This paper emphasis on building an extractive summarization system combining the features of principal component analysis for dimensionality reduction and bidirectional Recurrent Neural Networks and Long Short-Term Memory (RNN-LSTM) deep learning model for short and exact synopsis using seq2seq model. It presents a paradigm shift with regard to the way extractive summaries are generated. Novel algorithms for word extraction using assertions are proposed. The semantic framework is well-grounded in this research facilitating the correct decision making process after reviewing huge amount of online reviews, considering all its important features into account. The advantages of the proposed solution provides greater computational efficiency, better inferences from social media, data understanding, robustness and handling sparse data. Experiments on the different datasets also outperforms the previous researches and the accuracy is claimed to achieve more than the baselines, showing the efficiency and the novelty in the research paper. The comparisons are done by calculating accuracy with different baselines using Rouge tool. [ABSTRACT FROM AUTHOR]

Sentiment Analysis and Opinion Mining is a computational text processing technique used for extraction of emotion from the given text, for e.g. joy, sad, disgust, fear, anger which can be polarized as positive, negative and neutral. The advancement in technology and data augmentation has been an easy access for data collection for the research work. In this research paper, different machine learning algorithms such as Extreme Gradient Boost classifier, Extra tree classifier, K-Nearest Neighbour classifier and Long Short Term Memory deep learning model was computed to classify the divergent datasets such as Twitter Bengaluru traffic data, movie review, fake news classification and financial sentiments. Performance of these classifier was tabulated with respect to independent datasets in terms of accuracy, f1-score, precision, sensitivity, mean squared error and, log loss and graphically represented with the help of PyCharm. The contribution in this paper is a methodology that automates the sentiment analysis of the divergent dataset with context of apprehension of tweets. [ABSTRACT FROM AUTHOR]

The availability of legal judgment documents in digital form offers numerous opportunities for information extraction and application. Automatic summarization of these legal texts is a crucial and a challenging task due to the unusual structure and high complexity of these documents. Previous approaches in this direction have relied on huge labelled datasets, using hand engineered features, leveraging on domain knowledge and focussed their attention on a narrow sub-domain for increased effectiveness. In this paper, we propose simple generic techniques using neural network for the summarization task for Indian legal judgment documents. We explore two neural network architectures for this task utilizing the word and sentence embeddings for capturing the semantics. The main advantage of the proposed approaches is that they do not rely on hand crafted features, or domain specific knowledge, nor is their application restricted to a particular sub-domain thus making them suitable to be extended to other domains as well. We tackle the problem of unavailability of labelled data for the task by assigning classes/scores to sentences in the training set, based on their match with reference summary produced by humans. The experimental evaluations establish the effectiveness of our proposed approaches as compared with other baselines. [ABSTRACT FROM AUTHOR]

In this paper, we propose an approach to understand situations in the real world with the sentiment analysis of Twitter data base on deep learning techniques. With the proposed method, it is possible to predict user satisfaction of a product, happiness with some particular environment or destroy situation after disasters. Recently, deep learning is able to solve problems in computer vision or voice recognition, and convolutional neural network (CNN) works good for image analysis and image classification. The biggest reason to adopt CNN in image analysis and classification is due to CNN can extract an area of features from global information, and it is able to consider the relationship among these features. The above solution can achieve a higher accuracy in analysis and classification. For natural language processing, texts data features also can be extracted piece by piece and to consider the relationship among these features, but without the consideration of context or whole sentence, the sentiment might be understood wrong. And currently, convolutional neural network is one of the most effective methods to do image classification, CNN has a convolutional layer to extract information by a larger piece of text, so we work for sentiment analysis with convolutional neural network, and we design a simple convolutional neural network model and test it on benchmark, the result shows that it achieves better accuracy performance in twitter sentiment classification than some of traditional method such as the SVM and Naive Bayes methods. [ABSTRACT FROM AUTHOR]

The general method of machine learning has encountered disadvantages in terms of the significant amount of time and effort required for feature extraction and engineering in natural language processing. However, in recent years, these disadvantages have been solved using deep learning. In this paper, we propose a mention pair (MP) model using deep learning, and a system that combines both rule-based and deep learning-based systems using a guided MP as a coreference resolution, which is an information extraction technique. Our experiment results confirm that the proposed deeplearning based coreference resolution system achieves a better level of performance than rule- and statistics-based systems applied separately. [ABSTRACT FROM AUTHOR]