Sentence-level Sentiment Analysis Research Articles

Sentiment Analysis Using Deep Learning Approaches on Multi-Domain Dataset in Telugu Language

Recent advancements in Natural Language Processing (NLP) have made sentiment analysis an essential component of a variety of NLP jobs, including recommendation systems, question answering, and business intelligence products. While sentiment analysis research has, to put it mildly, been widely pursued in English, Telugu has barely ever attempted the task. The majority of research works concentrate on analysing the sentiments of Tweets, news, or reviews containing Hindi and English words. There is a growing interest among academics in studying how people express their thoughts and views in Indian languages like Bengali, Telugu, Malayalam, Tamil and so on. Due to a paucity of labelled datasets, microscopic investigation on Indian languages has been published to our knowledge. This work suggested a sentence-level sentiment analysis on multi-domain datasets that has been collected in Telugu. Deep learning models have been used in this work because it demonstrates the significant expertise in sentiment analysis and is widely regarded as the cutting-edge model in Telugu Sentiment Analysis. Our proposed work investigates a productive Bidirectional Long Short-Term Memory (BiLSTM) Network and Bidirectional GRU Network (BiGRU) for improving Telugu Sentiment Analysis by encapsulating contextual information from Telugu feature sequences using Forward-Backward encapsulation. Further, the model has been deployed by merging the domains so as to predict the accuracy and other performance metrics. The experimental test findings show that the deep learning models outperform when compared with the baseline traditional ML methods in four benchmark sentiment analysis datasets. There is evidence that the proposed sentiment analysis method has improved precision, recall, F1-score and accuracy in certain cases. The proposed model has achieved the F1-score of 86% for song datasets when compared with the other existing models.

FeDN2: Fuzzy-Enhanced Deep Neural Networks for Improvement of Sentence-Level Sentiment Analysis

Sentence-level sentiment analysis is a natural language processing model growing rapidly and strongly due to its role in artificial intelligence systems. There are many approaches to developing and improving the performance of sentence-level sentiment analysis with satisfactory performance, among which deep neural network methods are notable. However, sentence-level sentiment analysis methods based on deep neural networks often have two limitations: (i) The system architecture is not deep enough; (ii) Sentences containing unclear sentiments cannot be processed. To solve the above two challenges, in this paper, we propose a new sentence-level sentiment analysis method called Fuzzy-enhanced Deep Neural Networks (FeDN2) by deepening deep neural networks by adding fuzzy and defuzzy classes. FeDN2 includes the following main layers: (i) BERT layer to convert sentences into vectors. (ii) Fuzzification layer to blur sentence vectors. (iii) Deep convolutional layers to extract high-level features. (iv) Defuzzification layer to convert high-level feature vectors into clear values. (v) Fully connected layer to learn non-linear combinations of these high-level features. (vi) Classification layer to identify the sentiment polarity of sentences. FeDN2 was tested on two benchmark datasets. The results demonstrated that it can improve the performance of previous sentence-level sentiment analysis methods based on deep neural networks.

Uncovering the quality factors driving the success of mobile payment apps

This study comprehensively analyzed the key quality factors of mobile payment applications that shape consumer perceptions and their influence on market performance. Leveraging text analytics techniques, including Latent Dirichlet Allocation (LDA) topic modeling and sentence-level sentiment analysis, we analyzed a vast dataset of 230,940 reviews of nine mobile payment apps. Our investigation revealed four significant quality factors discussed in online consumer reviews: payment convenience, security, customer service, and app design. Crucially, this study demonstrated the substantial impact of positive and negative evaluations of these factors on the market performance of mobile payment apps, with numerical ratings acting as mediators. This study breaks new ground by empirically validating the link between post-usage evaluations and the app success. Additionally, it also empirically validated the link between post-usage evaluations and app success, elucidating the role of quality factors. The insights can empower app developers and marketers to enhance user experience and attain market dominance.

Sentence-level sentiment analysis based on supervised gradual machine learning

Sentence-level sentiment analysis (SLSA) aims to identify the overall sentiment polarity conveyed in a given sentence. The state-of-the-art performance of SLSA has been achieved by deep learning models. However, depending on the i.i.d (independent and identically distributed) assumption, the performance of these deep learning models may fall short in real scenarios, where the distributions of training and target data are almost certainly different to some extent. In this paper, we propose a supervised solution based on the non-i.i.d paradigm of gradual machine learning (GML) for SLSA. It begins with some labeled observations, and gradually labels target instances in the order of increasing hardness by iterative knowledge conveyance. It leverages labeled samples for supervised deep feature extraction, and constructs a factor graph based on the extracted features to enable gradual knowledge conveyance. Specifically, it employs a polarity classifier to detect polarity similarity between close neighbors in an embedding space, and a separate binary semantic network to extract implicit polarity relations between arbitrary instances. Our extensive experiments on benchmark datasets show that the proposed approach achieves the state-of-the-art performance on all benchmark datasets. Our work clearly demonstrates that by leveraging DNN for feature extraction, GML can easily outperform the pure DNN solutions.

MSGAT-Based Sentiment Analysis for E-Commerce

Sentence-level sentiment analysis, as a research direction in natural language processing, has been widely used in various fields. In order to address the problem that syntactic features were neglected in previous studies on sentence-level sentiment analysis, a multiscale graph attention network (MSGAT) sentiment analysis model based on dependent syntax is proposed. The model adopts RoBERTa_WWM as the text encoding layer, generates graphs on the basis of syntactic dependency trees, and obtains sentence sentiment features at different scales for text classification through multilevel graph attention network. Compared with the existing mainstream text sentiment analysis models, the proposed model achieves better performance on both a hotel review dataset and a takeaway review dataset, with 94.8% and 93.7% accuracy and 96.2% and 90.4% F1 score, respectively. The results demonstrate the superiority and effectiveness of the model in Chinese sentence sentiment analysis.

Resource Construction and Ensemble Learning based Sentiment Analysis for the Low-resource Language Uyghur

<p>To address the problem of scarce low-resource sentiment analysis corpus nowadays, this paper proposes a sentence-level sentiment analysis resource conversion method HTL based on the syntactic-semantic knowledge of the low-resource language Uyghur to convert high-resource corpus to low-resource corpus. In the conversion process, a k-fold cross-filtering method is proposed to reduce the distortion of data samples, which is used to select high-quality samples for conversion; finally, the Uyghur sentiment analysis dataset USD is constructed; the Baseline of this dataset is verified under the LSTM model, and the accuracy and F1 values reach 81.07% and 81.13%, respectively, which can provide a reference for the construction of low-resource language corpus nowadays. The accuracy and F1 values reached 81.07% and 81.13%, respectively, which can provide a reference for the construction of today’s low-resource corpus. Meanwhile, this paper also proposes a sentiment analysis model based on logistic regression ensemble learning, SA-LREL, which combines the advantages of several lightweight network models such as TextCNN, RNN, and RCNN as the base model, and the meta-model is constructed using logistic regression functions for ensemble, and the accuracy and F1 values reach 82.17% and 81.86% respectively in the test set, and the experimental results show that the method can effectively improve the performance of Uyghur sentiment analysis task.</p> <p> </p>

Sentiment analysis of weather news in British online newspapers

The advancement of modern technologies has influenced the way news is presented and consumed, particularly online. Weather is an important topic for the public as it relates to the human experience and addresses current societal issues. In this paper, we introduce a systematic approach to conduct sentiment analysis of weather news stories, to specify the emotional tone and examine the role of subjectivity in online news reporting. This research falls within the scope of a lexicon-based (unsupervised) approach to sentiment analysis, which involves finding the sentiment polarity of words. The analysis is predominantly based on sentence-level sentiment analysis. Two popular online web services, MonkeyLearn and SentiStrength, were applied to automatically detect human emotions. We compared the efficiency of each tool and found that MonkeyLearn provided better final results in comparison to SentiStrength, which tended to misclassify negative sentiments into neutral ones. The final results of frequency calculation showed the dominance of weather news stories with negative sentiment polarity over positive and neutral ones, with neutral sentiments being in the minority. Based on the empirical findings, we observed an objectivity-to-subjectivity shift in online news reporting.

Aspect-based Sentiment Analysis on Car Reviews Using SpaCy Dependency Parsing and VADER

All businesses, including car manufacturers, need to understand what aspects of their products are perceived as positive and negative based on user reviews so that they can make improvements for the negative aspects and maintain the already positive aspects of their products. One of the available tools for this task is Sentiment Analysis. The traditional document-level and sentence-level sentiment analysis will only classify each document / sentence into a class. This approach is incapable of finding the more fine-grained sentiment for a specific aspect of interest, for example, comfort, price, engine, paint, etc. Therefore, in this case, Aspect-based Sentiment Analysis is used. A total of 22.702 rows of car review data are scraped from the Edmunds website (www.edmunds.com) for a specific car manufacturer. Dependency Parsing and noun phrase extraction were carried out using the SpaCy module in Python, and VADER sentiment analysis was used to determine the polarity of the sentiment for each noun phrase. Results showed that the vast majority of the sentiments are on the positive aspects: comfortable to drive, good fuel economy / mileage, reliability, spaciousness, value for money, helpful rear camera, quiet ride, good acceleration, well-designed, good sound system, and solid build. The results for the negative aspects have some similar aspects with those in the positive class but has a very low frequency. This finding means that the vast majority of the users are satisfied with multiple aspects of the produced cars. The limitation of this research and future research direction are discussed.

Sentiment Analysis of Sentence-Level using Dependency Embedding and Pre-trained BERT Model

Sentiment analysis is a valuable field of research in NLP with many applications. Dependency tree is one of the language features that can be utilized in this field. Dependency embedding, as one of the semantic representations of a sentence, has shown to provide more significant results compared to other embeddings, which makes it a potential way to improve the performance of sentiment analysis tasks. This study aimed to investigate the effect of dependency embedding on sentence-level sentiment analysis through experimental research. The study replaced the Vocabulary Graph embedding in the VGCN-BERT sentiment classification system architecture with several dependency embedding representations, including word vector, context vector, average of word and context vectors, weighting on word and context vectors, and merging of word and context vectors. The experiments were conducted on two datasets, SST-2 and CoLA, with more than 19 thousand labeled sentiment sentences. The results indicated that dependency embedding can enhance the performance of sentiment analysis at the sentence level.

Khmer Sentiment Lexicon Based on PU Learning and Label Propagation Algorithm

The sentiment lexicon is an important tool for natural language processing tasks. In addition to being able to determine the sentiment polarity of words or phrases, it can assist attribute-level, sentence-level, and text-level sentiment analysis tasks. In light of the fact that tagging data and corpora for the Khmer language are scarce, where most resources related to sentiment lexicons are for English, this paper proposes a method for constructing a sentiment lexicon for Khmer based on Positive-Unlabeled learning (PU Learning) and the label propagation algorithm. Sentiment words are first extracted from a corpus using the Spy technique of PU learning method. The main idea is to purify the set of N-class examples, train the MLP classifier, and continuously delete spy words and increase the number of P-class words in the iterative process. Following this, the sentiment polarity of the candidate words is determined. By considering the problem of determining the sentiment polarity of the candidate words as one of calculating its probability distribution, a small number of labeled sentiment words and candidate words are used to construct a graph model. The contextual information of the candidate words is used to construct a simple supplementary graph model of the set of sentiment words through word co-occurrence and triangulation, where this enhances the correlation between data items. The sentiment polarity of the candidate words is then determined through the label propagation algorithm. The results of experiments show that the proposed method can be used to construct a Khmer sentiment lexicon with a small number of labeled data and a small corpus without requiring excessive manual labeling.

Artificial Intelligence Based Sentence Level Sentiment Analysis of COVID-19

Artificial Intelligence Based Sentence Level Sentiment Analysis of COVID-19

Retraction Note: Classification of sentence level sentiment analysis using cloud machine learning techniques

Retraction Note: Classification of sentence level sentiment analysis using cloud machine learning techniques

A Lexicon Enhanced Collaborative Network for targeted financial sentiment analysis

The increasing interest around emotions in online texts creates the demand for financial sentiment analysis. Previous studies mainly focus on coarse-grained document-/sentence-level sentiment analysis, which ignores different sentiment polarities of various targets (e.g., company entities) in a sentence. To fill the gap, from a fine-grained target-level perspective, we propose a novel Lexicon Enhanced Collaborative Network (LECN) for targeted sentiment analysis (TSA) in financial texts. In general, the model designs a unified and collaborative framework that can capture the associations of targets and sentiment cues to enhance the overall performance of TSA. Moreover, the model dynamically incorporates sentiment lexicons to guide the sentiment classification, which cultivates the model faculty of understanding financial expressions. In addition, the model introduces a message selective-passing mechanism to adaptively control the information flow between two tasks, thereby improving the collaborative effects. To verify the effectiveness of LECN, we conduct experiments on four financial datasets, including SemEVAL2017 Task5 subset1, SemEVAL2017 Task5 subset2, FiQA 2018 Task1, and Financial PhraseBank. Results show that LECN achieves improvements over the state-of-art baseline by 1.66 p.p., 1.47 p.p., 1.94 p.p., and 1.88 p.p. in terms of F1-score. A series of further analyses also indicate that LECN has a better capacity for comprehending domain-specific expressions and can achieve the mutually beneficial effect between tasks.

A complete framework for aspect-level and sentence-level sentiment analysis

A complete framework for aspect-level and sentence-level sentiment analysis

Understand Students Feedback Using Bi-Integrated CRF Model Based Target Extraction

Educational institutions showing interest to find the opinion of the students about their course and the instructors to enhance the teaching-learning process. For this, most research uses sentiment analysis to track students’ behavior. Traditional sentence-level sentiment analysis focuses on the whole sentence sentiment. Previous studies show that the sentiments alone are not enough to observe the feeling of the students because different words express different sentiments in a sentence. There is a need to extract the targets in a given sentence which helps to find the sentiment towards those targets. Target extraction is the subtask of targeted sentiment analysis. In this paper, we proposed the innovative model to find the targets of the given sentence using Bi-Integrated Conditional Random Fields (CRF). A Parallel fusion neural network model is designed to perform this task. We evaluate the model using the Michigan dataset and we build a dataset for target extraction from student reviews. The experimental results show that our proposed fusion model achieves better results compared to baseline models.

Balcony: A remembered architectural element amid pandemic: Evidences from digital media

The pandemic has created a global crisis. Governments have taken a number of preventative measures like “stay-at-home” orders to curb the spread of COVID-19. These measures have provided people to rediscover their living spaces. The balcony is one of these places. The balcony has a crucial role in human life and works as a connector in-between space of indoor-outdoor, public-private. However, in the 21st century, it left its glorious old days behind, lost its vitality, and turned into a faded architectural element. Along with the pandemic, the balcony is again on the people's agenda as space symbolizing the new form of freedom. The aim of this study is, on the one hand, to put forth the effects of the pandemic on the popularity of the balcony to employ quantitative analysis of internet search statistics; on the other hand, to reveal how pandemic affects people's perception of the balcony to use sentence-level sentiment analysis.

IFeel 2.0: A Multilingual Benchmarking System for Sentence-Level Sentiment Analysis

Sentiment analysis became a hot topic, specially with the amount of opinions available in social media data. With the increasing interest in this theme, several methods have been proposed in the literature. Recent efforts have showed that there is no single method that always achieves the best prediction performance for different datasets. Additionally, novel methods have not being extensively compared with other methods and across different datasets, specially methods that are not designed to the English language. Consequently, researchers tend to accept any popular method as a valid methodology to measure sentiments, a practice that is usual in science. In this context, we propose iFeel 2.0, an online web system that implements 19 sentence-level sentiment analysis methods and allows users to easily label a dataset with all of them. iFeel aims at easing the comparison of new methods with baseline approaches and can also be helpful for those interested in using sentiment analysis, allowing them to choose an appropriate sentiment analysis method that works fine for a new dataset. We also incorporate a multiple language feature to allow methods designed for specific languages to be easily compared with a baseline approach that simply translates the input data to English and run these 19 methods. We hope this system can represent an important contribution to this field. Sentiment analysis became a hot topic, specially with the amount of opinions available in social media data.With the increasing interest in this theme, several methods have been proposed in the literature. Recent effortshave showed that there is no single method that always achieves the best prediction performance for different datasets. Additionally, novel methods have not being extensively compared with other methods and across different datasets, specially methods that are not designed to the English language.Consequently, researchers tend to accept any popular method as a valid methodology to measure sentiments, a practice that is usual in science.In this context, we propose iFeel 2.0, an online web system that implements 19 sentence-level sentiment analysis methods and allows users to easily label a dataset with all of them. iFeel aims at easing the comparison of new methods with baseline approaches and can also be helpful for those interested in using sentiment analysis, allowing them to choose an appropriate sentiment analysis method that works fine for a new dataset.We also incorporate a multiple language feature to allow methods designed for specific languages to be easily compared with a baseline approach that simply translates the input data to English and run these 19 methods. We hope this system can represent an important contribution to this field.

Sentiment Analysis Using XLM-R Transformer and Zero-shot Transfer Learning on Resource-poor Indian Language

Sentiment analysis on social media relies on comprehending the natural language and using a robust machine learning technique that learns multiple layers of representations or features of the data and produces state-of-the-art prediction results. The cultural miscellanies, geographically limited trending topic hash-tags, access to aboriginal language keyboards, and conversational comfort in native language compound the linguistic challenges of sentiment analysis. This research evaluates the performance of cross-lingual contextual word embeddings and zero-shot transfer learning in projecting predictions from resource-rich English to resource-poor Hindi language. The cross-lingual XLM-RoBERTa classification model is trained and fine-tuned using the English language Benchmark SemEval 2017 dataset Task 4 A and subsequently zero-shot transfer learning is used to evaluate the classification model on two Hindi sentence-level sentiment analysis datasets, namely, IITP-Movie and IITP-Product review datasets. The proposed model compares favorably to state-of-the-art approaches and gives an effective solution to sentence-level (tweet-level) analysis of sentiments in a resource-poor scenario. The proposed model compares favorably to state-of-the-art approaches and achieves an average performance accuracy of 60.93 on both the Hindi datasets.

제품 출시 초기의 고객 불만 모니터링을 위한 소셜미디어 마이닝 접근법

This study suggests a social media mining approach for monitoring critical complaints in the early stage of product launch via word embedding, clustering and sentiment analysis. This approach selectively uses social media product reviews created in the beginning stage of product launch. Word embedding and clustering are used to identify customer complaint factors from reviews. Next, sentence-level sentiment analysis is conducted based on the understanding of review writing pattern, thereby calculating urgency and severity in a quantitative manner. Finally, a customer-stated complaint portfolio map is developed, showing critical complaint factors. In the case study of smartphone ‘Galaxy S10’, the critical complaint factors related to Samsung pay connection error, and fingerprint recognition are identified, which have been rapidly improved since the product launch, indeed. We expect that this approach contributes to identifying critical customer complaints in the early stage, in addition to enabling the prompt response to customer complaints.

Lexicon‐pointed hybrid N‐gram Features Extraction Model (LeNFEM) for sentence level sentiment analysis

AbstractSentiment analysis of social media textual posts can provide information and knowledge that is applicable in social settings, business intelligence, evaluation of citizens' opinions in governance, and in mood triggered devices in the Internet of Things. Feature extraction and selection is a key determinant of accuracy and computational cost of machine learning models for such analysis. Most feature extraction and selection techniques utilize bag of words, N‐grams, and frequency‐based algorithms especially Term Frequency‐Inverse Document Frequency. However, these approaches do not consider relationships between words, they ignore words' characteristics and they suffer high feature dimensionality. In this paper we propose and evaluate a feature extraction and selection approach that utilizes a fixed hybrid N‐gram window for feature extraction and minimum redundancy maximum relevance feature selection algorithm for sentence level sentiment analysis. The approach improves the existing features extraction techniques, specifically the N‐gram by generating a hybrid vector from words, Part of Speech (POS) tags, and word semantic orientation. The vector is extracted by using a static trigram window identified by a lexicon where a sentiment word appears in a sentence. A blend of the words, POS tags, and the sentiment orientations of the static trigram are used to build the feature vector. The optimal features from the vector are then selected using minimum redundancy maximum relevance (MRMR) algorithm. Experiments were carried out using the public Yelp dataset to compare the performance of the proposed model and existing feature extraction models (BOW, normal N‐grams and lexicon‐based bag of words semantic orientations). Using supervised machine learning classifiers the experimental results showed that the proposed model had the highest F‐measure (88.64%) compared to the highest (83.55%) from baseline approaches. Wilcoxon test carried out ascertained that the proposed approach performed significantly better than the baseline approaches. Comparative performance analysis with other datasets further affirmed that the proposed approach is generalizable.