An artificial neural network based approach for sentiment analysis of opinionated text

Abstract: This paper aims at improving the system which is submitted to the shared task on Sentiment Analysis in Indian Languages (SAIL2015) at MIKE 2015. In this work the tweets are classified into three polarity category namely positive, negative and neutral. Twitter data of three languages namely Tamil, Hindi and Bengali are already provided by SAIL 2015 task organizers as we have participated in the contest. Recurrent neural network is used for analyzing the sentiment in the tweets. The system performs well for recurrent neural network when compared with the system submitted to the shared task as the accuracy of the system had increased. This is due to the fact that the recurrent neural network concentrates more on language specific feature. In training, the recurrent neural network tries to learn based on the error that are generated as intermediate output. By this way the network seeks to pursue sentiment oriented feature which improves in analyzing the sentiments on tweets. We have obtained a state accuracy for the proposed system, where we achieved an accuracy of 88%, 72.01% and 65.16% for Tamil, Hindi and Bengali languages respectively for SAIL 2015 dataset.

Abstract: Interest in research involving health-medical information analysis based on artificial intelligence, especially for deep learning techniques, has recently been increasing. Most of the research in this field has been focused on searching for new knowledge for predicting and diagnosing disease by revealing the relation between disease and various information features of data. These features are extracted by analyzing various clinical pathology data, such as EHR (electronic health records), and academic literature using the techniques of data analysis, natural language processing, etc. However, still needed are more research and interest in applying the latest advanced artificial intelligence-based data analysis technique to bio-signal data, which are continuous physiological records, such as EEG (electroencephalography) and ECG (electrocardiogram). Unlike the other types of data, applying deep learning to bio-signal data, which is in the form of time series of real numbers, has many issues that need to be resolved in preprocessing, learning, and analysis. Such issues include leaving feature selection, learning parts that are black boxes, difficulties in recognizing and identifying effective features, high computational complexities, etc. In this paper, to solve these issues, we provide an encoding-based Wave2vec time series classifier model, which combines signal-processing and deep learning-based natural language processing techniques. To demonstrate its advantages, we provide the results of three experiments conducted with EEG data of the University of California Irvine, which are a real-world benchmark bio-signal dataset. After converting the bio-signals (in the form of waves), which are a real number time series, into a sequence of symbols or a sequence of wavelet patterns that are converted into symbols, through encoding, the proposed model vectorizes the symbols by learning the sequence using deep learning-based natural language processing. The models of each class can be constructed through learning from the vectorized wavelet patterns and training data. The implemented models can be used for prediction and diagnosis of diseases by classifying the new data. The proposed method enhanced data readability and intuition of feature selection and learning processes by converting the time series of real number data into sequences of symbols. In addition, it facilitates intuitive and easy recognition, and identification of influential patterns. Furthermore, real-time large-capacity data analysis is facilitated, which is essential in the development of real-time analysis diagnosis systems, by drastically reducing the complexity of calculation without deterioration of analysis performance by data simplification through the encoding process.

Abstract: With the evolution of e-commerce and Online Social Networks, the web information has constantly increased, so the relevance to create methods for automatic knowledge extraction and data mining earned notoriety. Information as opinion evaluation is a point studied by Sentiment Analysis area, which is becoming important nowadays. Be aware of the best reviews is a factor that must be taken into account. Sousa et al. proposed an approach to estimate the degree of importance of reviews about product and services using Fuzzy System, reporting good results. This work proposes an experimental study between their approach using Fuzzy Systems and an execution using Artificial Neural Network to verify which is the most appropriate to solve the problem to estimate the importance of reviews.

Abstract: The conference “SIIE” aims to develop the dialogue between experts and researchers from public and private sectors, to acquire basic and experimental on Information Systems (IS) and Economic Intelligence (EI) (or Competitive Intelligence in English acceptance and terminology). This promotes, in a risk environment, technologies related to economic intelligence. The dynamic of EI depends on the control of knowledge and requires competences to design the best strategies and ensure that decision-­makers take the right decisions. The international conference SIIE will be held in its seventh (7th.) edition in Marrakech in April 2017, after the six successful editions. This edition is organized by CIEMS and IEEE Technology & Engineering Management Society (TEMS), and sponsored by the Universities of Maghreb and Europe countries. The theme of SIIE is « Trends in Technology Management and Economic Intelligence ». Since 2008, the six proceedings and editions have allowed academic researchers and economic actors to achieve completed projects. The goal of SIIE is to continue in this way by creating opportunities, ideas and innovative ways to enhance projects, and build connections between universities and industries on both sides of the Mediterranean Sea. SIIE'2017 includes keynotes, tutorials, authors’ sessions and industrial panels, animated by experts, to identify new approaches and knowledge in economic intelligence, applied research and feedback. This will allow the emergence of new clusters in competitive intelligence. Within a convivial and comfortable framework, as Morocco knows so well how to offer such a framework, the SIIE conference has always been thought to promote the weaving of trust networks between actors in academia, industry and politics, thus contributing to the training of the SIIE scientific community. The expert recommendations and advices will help the SIIE community to find solutions to their many questions and problems.

Abstract: What factors predict the underreporting of sexual harassment in academe? We used logistic regression and sentiment analysis to examine 2,343 reports of sexual harassment involving members of university communities. Results indicate students were 1.6 times likely to not report their experiences when compared to faculty. Respondents in the life and physical sciences were 1.7 times more likely to not report their experiences when compared to respondents in other disciplines. Men represented 90% of the reported perpetrators of sexual harassment. Analysis of respondents' written accounts show variation of overall sentiment based on discipline, student type, and the type of institution attended, particularly with regard to mental health. Our results suggest that institutional and departmental barriers driven by power asymmetries play a large role in the underreporting sexual harassment among students-especially those in STEM disciplines.

Abstract: We consider the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative. Using movie reviews as data, we flnd that standard machine learning techniques deflnitively outperform human-produced baselines. However, the three machine learning methods we employed (Naive Bayes, maximum entropy classiflcation, and support vector machines) do not perform as well on sentiment classiflcation as on traditional topic-based categorization. We conclude by examining factors that make the sentiment classiflcation problem more challenging.

Abstract: Merchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows rapidly. For a popular product, the number of reviews can be in hundreds or even thousands. This makes it difficult for a potential customer to read them to make an informed decision on whether to purchase the product. It also makes it difficult for the manufacturer of the product to keep track and to manage customer opinions. For the manufacturer, there are additional difficulties because many merchant sites may sell the same product and the manufacturer normally produces many kinds of products. In this research, we aim to mine and to summarize all the customer reviews of a product. This summarization task is different from traditional text summarization because we only mine the features of the product on which the customers have expressed their opinions and whether the opinions are positive or negative. We do not summarize the reviews by selecting a subset or rewrite some of the original sentences from the reviews to capture the main points as in the classic text summarization. Our task is performed in three steps: (1) mining product features that have been commented on by customers; (2) identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative; (3) summarizing the results. This paper proposes several novel techniques to perform these tasks. Our experimental results using reviews of a number of products sold online demonstrate the effectiveness of the techniques.

Abstract: We consider the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative. Using movie reviews as data, we find that standard machine learning techniques definitively outperform human-produced baselines. However, the three machine learning methods we employed (Naive Bayes, maximum entropy classification, and support vector machines) do not perform as well on sentiment classification as on traditional topic-based categorization. We conclude by examining factors that make the sentiment classification problem more challenging.

Abstract: This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended (thumbs down). The classification of a review is predicted by the average semantic orientation of the phrases in the review that contain adjectives or adverbs. A phrase has a positive semantic orientation when it has good associations (e.g., "subtle nuances") and a negative semantic orientation when it has bad associations (e.g., "very cavalier"). In this paper, the semantic orientation of a phrase is calculated as the mutual information between the given phrase and the word "excellent" minus the mutual information between the given phrase and the word "poor". A review is classified as recommended if the average semantic orientation of its phrases is positive. The algorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations). The accuracy ranges from 84% for automobile reviews to 66% for movie reviews.

Abstract: This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended (thumbs down) The classification of a review is predicted by the average semantic orientation of the phrases in the review that contain adjectives or adverbs A phrase has a positive semantic orientation when it has good associations (eg, “subtle nuances”) and a negative semantic orientation when it has bad associations (eg, “very cavalier”) In this paper, the semantic orientation of a phrase is calculated as the mutual information between the given phrase and the word “excellent” minus the mutual information between the given phrase and the word “poor” A review is classified as recommended if the average semantic orientation of its phrases is positive The algorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations) The accuracy ranges from 84% for automobile reviews to 66% for movie reviews