Predicting Supervise Machine Learning Performances for Sentiment Analysis Using Contextual-Based Approaches

The rise of social media such as blogs and social networks has fueled interest in sentiment analysis. With the proliferation of reviews, ratings, recommendations and other forms of online expression, online opinion has turned into a kind of virtual currency for businesses looking to market their products, identify new opportunities and manage their reputations, therefore many are now looking to the field of sentiment analysis. In this paper, we present a feature-based sentence level approach for Arabic sentiment analysis. Our approach is using Arabic idioms/saying phrases lexicon as a key importance for improving the detection of the sentiment polarity in Arabic sentences as well as a number of novels and rich set of linguistically motivated features contextual Intensifiers, contextual Shifter and negation handling), syntactic features for conflicting phrases which enhance the sentiment classification accuracy. Furthermore, we introduce an automatic expandable wide coverage polarity lexicon of Arabic sentiment words. The lexicon is built with gold-standard sentiment words as a seed which is manually collected and annotated and it expands and detects the sentiment orientation automatically of new sentiment words using synset aggregation technique and free online Arabic lexicons and thesauruses. Our data focus on modern standard Arabic (MSA) and Egyptian dialectal Arabic tweets and microblogs (hotel reservation, product reviews, etc.). The experimental results using our resources and techniques with SVM classifier indicate high performance levels, with accuracies of over 95%.

The social media space has evolved into a large labyrinth of information exchange platform and due to the growth in the adoption of different social media platforms, there has been an increasing wave of interests in sentiment analysis as a paradigm for the mining and analysis of users’ opinions and sentiments based on their posts. In this paper, we present a review of contextual sentiment analysis on social media entries with a specific focus on Twitter. The sentimental analysis consists of two broad approaches which are machine learning which uses classification techniques to classify text and is further categorized into supervised learning and unsupervised learning; and the lexicon-based approach which uses a dictionary without using any test or training data set, unlike the machine learning approach.

The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans. This task is, however, not one which a computer can perform by default. Identifying sentiments in an automated, algorithmic manner will be a useful capability for business and research in their search to understand what consumers think about their products or services and to understand human sociology. Here we propose two new Genetic Algorithms (GAs) for the task of automated text sentiment analysis. The GAs learn whether words occurring in a text corpus are either sentiment or amplifier words, and their corresponding magnitude. Sentiment words, such as 'horrible', add linearly to the final sentiment. Amplifier words in contrast, which are typically adjectives/adverbs like 'very', multiply the sentiment of the following word. This increases, decreases or negates the sentiment of the following word. The sentiment of the full text is then the sum of these terms. This approach grows both a sentiment and amplifier dictionary which can be reused for other purposes and fed into other machine learning algorithms. We report the results of multiple experiments conducted on large Amazon data sets. The results reveal that our proposed approach was able to outperform several public and/or commercial sentiment analysis algorithms.

The existing methods for Chinese sentiment Labeling mainly relies on the artificial sentiment corpus, but a sentiment word in the corpus may not be sentiment words in different sentences. This paper proposes a new method to label the words in the sentences by combining deep convolution neural network with sequential algorithm., We first extract the aspects comprised by words vectors, part of speech vectors, dependent syntax vectors to train the deep convolution neural network, and then employ the sequential algorithm to obtain the sentiment annotation of the sentence. Experimental results verify that our method is effective for sentiment labeling. Considering that the identification of the implicit aspects can improve the completeness of sentiment analysis, we suggest to construct the tuples including aspect, sentiment shifter, sentiment intensity, sentiment words after obtaining the sentiment labels for each word in the sentence. We develop new algorithm for implicit aspect identification by taking the two key factors of the aspects as a topic and the match degree of aspects and sentiment words, and the human language habit. The experiment demonstrates that the algorithm can effectively identify the implicit aspect. In this paper, we solve the problem of sentiment labeling and implicit aspect recognition in sentiment analysis. As a new tool for sentiment analysis, our method can be applied to the enterprise management information analysis, such as product online review, product online reputation, brand image and consumer preference management, and can also be used for the sentiment analysis of large-scale text data.

Based on Web 2.0 technology, more and more people tend to express their attitude or opinions on the Internet. Radical ideas, rumors, terrorism, or violent contents are also propagated on the Internet, causing several incidents of social panic every year in China. In fact, most of this content comprises joking or emotional catharsis. To detect this with conventional techniques usually incurs a large false alarm rate. To address this problem, this paper introduces a technique that combines sentiment analysis with background checks. State-of-the-art sentiment analysis usually depends on training datasets in a specific topic area. Unfortunately, for some domains, such as violence risk speech detection, there is no definitive training data. In particular, topic-independent sentiment analysis of short Chinese text has been rarely reported in the literature. In this paper, the violence risk of the Chinese microblogs is calculated from multiple perspectives. First, a lexicon-based method is used to retrieve violence-related microblogs, and then a similarity-based method is used to extract sentiment words. Semantic rules and emoticons are employed to obtain the sentiment polarity and sentiment strength of short texts. Second, the activity risk is calculated based on the characteristics of part of speech (PoS) sequence and by semantic rules, and then a threshold is set to capture the key users. Finally, the risk is confirmed by historical speeches and the opinions of the friend-circle of the key users. The experimental results show that the proposed approach outperforms the support vector machine (SVM) method on a topic-independent corpus and can effectively reduce the false alarm rate.

Sentiment analysis has become a powerful tool in processing and analysing expressed opinions on a large scale. While the application of sentiment analysis on English-language content has been widely examined, the applications on the Russian language remains not as well-studied. In this survey, we comprehensively reviewed the applications of sentiment analysis of Russian-language content and identified current challenges and future research directions. In contrast with previous surveys, we targeted the applications of sentiment analysis rather than existing sentiment analysis approaches and their classification quality. We synthesised and systematically characterised existing applied sentiment analysis studies by their source of analysed data, purpose, employed sentiment analysis approach, and primary outcomes and limitations. We presented a research agenda to improve the quality of the applied sentiment analysis studies and to expand the existing research base to new directions. Additionally, to help scholars selecting an appropriate training dataset, we performed an additional literature review and identified publicly available sentiment datasets of Russian-language texts.

This paper presents advancements in machine learning and cloud deployment that enable rapid and accurate automated lithology interpretation. A supervised machine learning technique is described that enables rapid, consistent, and accurate lithology prediction alongside quantitative uncertainty from large wireline or logging-while-drilling (LWD) datasets. To leverage supervised machine learning, a team of geoscientists and petrophysicists made detailed lithology interpretations of wells to generate a comprehensive training dataset. Lithology interpretations were based on applying determinist cross-plotting by utilizing and combining various raw logs. This training dataset was used to develop a model and test a machine learning pipeline. The pipeline was applied to a dataset previously unseen by the algorithm, to predict lithology. A quality checking process was performed by a petrophysicist to validate new predictions delivered by the pipeline against human interpretations. Confidence in the interpretations was assessed in two ways. The prior probability was calculated, a measure of confidence in the input data being recognized by the model. Posterior probability was calculated, which quantifies the likelihood that a specified depth interval comprises a given lithology. The supervised machine learning algorithm ensured that the wells were interpreted consistently by removing interpreter biases and inconsistencies. The scalability of cloud computing enabled a large log dataset to be interpreted rapidly; >100 wells were interpreted consistently in five minutes, yielding >70% lithological match to the human petrophysical interpretation. Supervised machine learning methods have strong potential for classifying lithology from log data because: 1) they can automatically define complex, non-parametric, multi-variate relationships across several input logs; and 2) they allow classifications to be quantified confidently. Furthermore, this approach captured the knowledge and nuances of an interpreter's decisions by training the algorithm using human-interpreted labels. In the hydrocarbon industry, the quantity of generated data is predicted to increase by >300% between 2018 and 2023 (IDC, Worldwide Global DataSphere Forecast, 2019–2023). Additionally, the industry holds vast legacy data. This supervised machine learning approach can unlock the potential of some of these datasets by providing consistent lithology interpretations rapidly, allowing resources to be used more effectively.

Fourier ptychographic microscopy (FPM) is a newly developed microscopic technique for large field of view, high-resolution and quantitative phase imaging by combining the techniques from ptychographic imaging, aperture synthesizing and phase retrieval. In FPM, an LED array is utilized to illuminate the specimen from different angles and the corresponding intensity images are synthesized to reconstruct a high-resolution complex field. As a flexible and low-cost approach to achieve high-resolution, wide-field and quantitative phase imaging, FPM is of enormous potential in biomedical applications such as hematology and pathology. Conventionally, the FPM reconstruction problem is solved by using a phase retrieval method, termed Alternate Projection. By iteratively updating the Fourier spectrum with low-resolution-intensity images, the result converges to a high-resolution complex field. Here we propose a new FPM reconstruction framework with deep learning methods and design a multiscale, deep residual neural network for FPM reconstruction. We employ the widely used open-source deep learning library PyTorch to train and test our model and carefully choose the hyperparameters of our model. To train and analyze our model, we build a large-scale simulation dataset with an FPM imaging model and an actual dataset captured with an FPM system. The simulation dataset and actual dataset are separated as training datasets and test datasets, respectively. Our model is trained with the simulation training dataset and fine tuned with the fine-tune dataset, which contains actual training data. Both our model and the conventional method are tested on the simulation test dataset and the actual test dataset to evaluate the performances. We also show the reconstruction result of another neural network-based method for comparison. The experiments demonstrate that our model achieves better reconstruction results and consumes much less time than conventional methods. The results also point out that our model is more robust under system aberrations such as noise and blurring (fewer intensity images) compared with conventional methods.

Interactive labelling of a multivariate dataset for supervised machine learning using linked visualisations, clustering, and active learning

Consumers reviews on ecommerce websites, online services, ratings and experience stories are useful for the user as well as the vendor. The reviewer can increase their brand’s loyalty and help other customers understand their experience with the product. Similarly reviews help the vendors gain more profiles by increasing their sale of products, if consumers leave positive feedback on their product review. But unfortunately, these review mechanisms can be misused by vendors. For example, one may create fake positive reviews to promote brand’s reputation or try to demote competitor’s products by leaving fake negative reviews on their product. Existing solutions with supervised include application of different machine learning algorithms and different tools like Weka. Unlike the existing work, instead of using a constrained dataset I chose to have a wide variety of vocabulary to work on such as different subjects of datasets combined as one big data set. Sentiment analysis has been incorporated based on emojis and text content in the reviews. Fake reviews are detected and categorized. The testing results are obtained through the application of Naïve Bayes, Linear SVC, Support Vector Machine and Random forest algorithms. The implemented (proposed) solution is to classify these reviews into fake or genuine. The highest accuracy is obtained by using Naïve Bayes by including sentiment classifier.

Emotion detection (ED) and sentiment analysis (SA) play a vital role in identifying an individual’s level of interest in any given field. Humans use facial expressions, voice pitch, gestures, and words to convey their emotions. Emotion detection and sentiment analysis in English and Chinese have received much attention in the last decade. Still, poor-resource languages such as Urdu have been mostly disregarded, which is the primary focus of this research. Roman Urdu should also be investigated like other languages because social media platforms are frequently used for communication. Roman Urdu faces a significant challenge in the absence of corpus for emotion detection and sentiment analysis because linguistic resources are vital for natural language processing. In this study, we create a corpus of 1021 sentences for emotion detection and 20,251 sentences for sentiment analysis, both obtained from various areas, and annotate it with the aid of human annotators from six and three classes, respectively. In order to train large-scale unlabeled data, the bag-of-word, term frequency-inverse document frequency, and Skip-gram models are employed, and the learned word vector is then fed into the CNN-LSTM model. In addition to our proposed approach, we also use other fundamental algorithms, including a convolutional neural network, long short-term memory, artificial neural networks, and recurrent neural networks for comparison. The result indicates that the CNN-LSTM proposed method paired with Word2Vec is more effective than other approaches regarding emotion detection and evaluating sentiment analysis in Roman Urdu. Furthermore, we compare our based model with some previous work. Both emotion detection and sentiment analysis have seen significant improvements, jumping from an accuracy of 85% to 95% and from 89% to 93.3%, respectively.

Opinion mining aiming to automatically detect subjective information has raised more and more interests from both academic and industry fields in recent years. In order to enhance the performance of opinion mining, some ensemble methods have been investigated and proven to be effective theoretically and empirically. However, cluster based ensemble method is paid less attention to in the area of opinion mining. In this paper, a new cluster based ensemble method, FCE-SVM, is proposed for opinion mining from social media. Based on the philosophy of divide and conquer, FCE-SVM uses fuzzy clustering module to generate different training sub datasets in the first stage. Then, base learners are trained based on different training datasets in the second stage. Finally, fusion module is employed to combine the results of based learners. Moreover, the multi-domain opinion datasets were investigated to verify the effectiveness of proposed method. Empirical results reveal that FCE-SVM gets the best performance through reducing bias and variance simultaneously. These results illustrate that FCE-SVM can be used as a viable method for opinion mining.

Online networking has gotten more consideration these days. Public and private sentiment about a wide assortment of subjects are communicated and spread consistently by means of various internet based life. Twitter is one of the internet based life plateform that is picking up notoriety. Twitter offers associations a quick and compelling approach to break down clients' viewpoints toward the basic to achievement in the commercial center. Building up a program for sentiment analysis is a way to deal with is utilized to computationally quantify client’s recognitions. Twitter sentiment analysis is the method for recognizing feelings and polarity in tweets. The primary computational strides right now deciding the extremity or notion of the tweet and afterward ordering them into the positive tweet or negative tweet or neutral tweet. The essential issue with Twitter sentiment analysis is the distinguishing proof of the most appropriate sentiment classifier that can accurately group the tweets. For the most part, base classification methods like Naive Bayes classifier, Random Forest classifier, SVMs and so on are being utilized. The objective of this paper is to anticipate feelings for the given Twitter post utilizing Python. Sentiment analysis can predict a wide range of feelings joined to the content, however right now 3 significant were considered: positive, negative and neutral. The training dataset is (a little more than 5900 models) and the information inside it is exceptionally skewed, which incredibly affected on the trouble of building great classifier. Subsequent to making a great deal of custom highlights, using both bag-of-words and word2vec portrayals and applying distinctive classification techniques, we accomplish great precision and accuracy for 3 emotions.

As the social applications are gaining the more popularity, different kinds of social media platform are ready to publish and express the emotions in the form of reviews. In which, detecting the concealed sentiment patterns and discovering knowledge in the huge user-generated inputs is a challenging task and has greater social significance value. In traditional sentiment analysis approaches, statistical correlation between words is considered. Whereas, dependency factor between aspects and the sentiment words are ignored, which has a greater impact factor on overall sentiment analysis. In this paper, we propose a new supervised topic level sentiment model (SSM), which is capable of handling overall sentiment analysis problems. Belief maximisation algorithm is used in SSM model, and Dirichlet distribution is used to estimate aspects and sentiment words. In order to prepare and modernise new documents, a hyperparameter Gibbs sampling method is used. We conducted experiments on reviews related to different products in multiple documents and the results state that the SSM model outperforms the on-hand algorithm in terms of aspect recognition and overall sentiment prediction accuracy.

As the social applications are gaining the more popularity, different kinds of social media platform are ready to publish and express the emotions in the form of reviews. In which, detecting the concealed sentiment patterns and discovering knowledge in the huge user-generated inputs is a challenging task and has greater social significance value. In traditional sentiment analysis approaches, statistical correlation between words is considered. Whereas, dependency factor between aspects and the sentiment words are ignored, which has a greater impact factor on overall sentiment analysis. In this paper, we propose a new supervised topic level sentiment model (SSM), which is capable of handling overall sentiment analysis problems. Belief maximisation algorithm is used in SSM model, and Dirichlet distribution is used to estimate aspects and sentiment words. In order to prepare and modernise new documents, a hyperparameter Gibbs sampling method is used. We conducted experiments on reviews related to different products in multiple documents and the results state that the SSM model outperforms the on-hand algorithm in terms of aspect recognition and overall sentiment prediction accuracy.