Sentiment Words Research Articles

Definition modeling: literature review and dataset analysis

<abstract><p>Definition modeling, the task of generating a definition for a given term, is a relatively new area of research applied in evaluating word embeddings. Automatic generation of dictionary quality definitions has many applications in natural language processing, such as sentiment analysis, machine translation, and word sense disambiguation. Additionally, definition modeling is also helpful for evaluating the quality of word embeddings. As more research is done in this field, the need for a summary of different applications, approaches, and obstacles grows apparent. This review provides an overview of the current research in definition modeling and a list of future directions and trends.</p></abstract>

Sentiment Thesaurus, Synset and Word2Vec Based Improvement in Bigram Model for Classifying Product Reviews.

Classifying product reviews is one of the tasks in Natural Language Processing by which the sentiment of the reviewer towards a product can be identified. This identification is useful for the growth of the business by increasing the number of satisfied customers through product quality improvement. Bigram models are more popular in performing this classification since it considers the occurrence of two words consecutively in the reviews. In the existing works on bigram models, semantically similar words to the words present in bigrams are not considered. As the reviewers use different words with the same meaning to express their feeling, we proposed improved bigram models in which semantically similar words to the words in bigrams are also used for classifying the reviews. In the proposed models, sentiment polarity thesaurus is constructed by including sentiment words and their synonyms. The combinations of constructed thesaurus, Synset and Word2Vec are used for extracting synonyms for the words in the reviews. Performance of the proposed models is compared with the traditional bigram model and state-of-the-art methods. It is observed from the results that our models are able to achieve better performance than traditional model and recent methods.

A Sentiment Analysis Approach to Discover Public Panic: Based on Weibo Covid-19 Data

Background: Weibo is a Twitter-like micro-blog platform in China where people post their real-life events as well as express their feelings in short texts. Since the outbreak of the Covid-19 pandemic, thousands of people have expressed their concerns and worries about the outbreak via Weibo, showing the existence of public panic. Methods: This paper comes up with a sentiment analysis approach to discover public panic. First, we used Octoparse to obtain Weibo posts about the hot topic Covid-19 Pandemic. Second, we break down those sentences into independent words and clean the data by removing stop words. Then, we use the sentiment score function that deals with negative words, adverbs, and sentiment words to get the sentiment score of each Weibo post. Results: We observe the distribution of sentiment scores and get the benchmark to evaluate public panic. Also, we apply the same process to test the mass sentiment under other topics to test the efficiency of the sentiment function, which shows that our function works well.

A Study of the Application of Weight Distributing Method Combining Sentiment Dictionary and TF-IDF for Text Sentiment Analysis

The most commonly used methods in text sentiment analysis are rule-based sentiment dictionary and machine learning, with the later referring to the use of vectors to represent text followed by the use of machine learning to classify the vectors. Both methods have their limitations, including inflexibility of rules, non-prominence of sentiment words. In this paper, we design a weight distributing method combining the two methods for text sentiment analysis, by which the sentence vectors obtained can both highlight words with sentiment meanings while retaining their text information. Empirical results show that based on this new method, the accuracy rate of text sentiment analysis can reach as high as 82.1%, which means 13.9% higher than rule-based sentiment dictionary method, and 7.7% higher than TF-IDF weighting method.

Sentiment-Target Word Pair Extraction Model Using Statistical Analysis of Sentence Structures

Product information has been propagated online via forums and social media. Lots of merchandise are recommended via an expert system method and is considered for purchase by online comments or product reviews. For predicting people’s opinions on products, studying people’s thoughts via extracting information in documents is referred to as sentiment analysis. Finding sentiment-target word pairs is an important sentiment mining research issue. With the Korean language, as the predicate appears at the very end, it is not easy to find the exact word pairs without first identifying the syntactic structure of the sentence. In this study, we propose a model that parses sentence structures and extracts sentiment-target word pairs from the parse tree. The proposed model extracts the sentiment-target word pairs that appear in the sentence by using parsing and statistical methods. For extracting sentiment-target word pairs, this model uses a sentiment word extractor and a target word extractor. After testing data from 4000 movie reviews, the applicable model showed high performance in both accuracy 93.25 (+14.45) and F1-score 82.29 (+3.31) compared with others. However, improvements in the recall rate (−0.35) are needed and computational costs must be reduced.

Language and Domain Specificity: A Chinese Financial Sentiment Dictionary

Abstract We use Word2vec to develop a financial sentiment dictionary from 3.1 million Chinese-language financial news articles. Our dictionary maps semantically similar words to a subset of human-expert generated financial sentiment words. In validation tests, our dictionary scores the sentiment of articles consistently with human reading of full articles. In return association tests, our dictionary outperforms and subsumes previous Chinese financial sentiment dictionaries, such as direct translations of Loughran and McDonald’s (2011, Journal of Finance, 66, 35–65) English-language financial dictionary. We also generate a list of politically related positive words that is unique to China; we find that this list has a weaker association with returns than does the list of other positive words. We demonstrate that state media uses more politically related positive and fewer negative words, and exhibits a sentiment bias. This bias renders the state media’s sentiment as less return-informative. Our findings demonstrate that dictionary-based sentiment analysis exhibits strong language and domain specificity.

Shifting the Blame: Storm and Wildfire Dramatic Images in American News Media

Some media frames might be likely to seek to evoke a certain sentiment, and that natural disaster coverage by the media focuses on the current impact of disasters. In their coverage, American news media use polar sentiment words to create bleeding images of natural disasters, potentially counter-productive to the wisdom of dealing with the natural disaster. Identifying the sentiment words that lead to a misperception of natural disasters can help journalists adopt the wisdom that natural disasters are not a human enemy. The corpus-assisted discourse studies (CADS) reported in this article investigates the American media's issues for dramatic reporting and the polar sentiment words utilized in the framing. The corpus is built from 100 news articles reporting wildfires and storms by ten major online American news media published from January 1, 2018, through December 31, 2020. It uses AntConc to generate word-list and word-link from which it identifies the dominant issues. Subsequently, it compares the AntConc word-list with A List of Sentiment Words to reveal the tones and dramatic imaging. The findings show that the dominant issues in storm reporting are description, impact, and prediction, while wildfire reporting are cause, impact, action, and prediction. The negative polar words produce dramatic images of storm as a violent beast and wildfire as a vengeful invader. Such description is provocative to blaming natural disasters as a cause of human suffering rather than improving our behaviors to reduce the suffering. Thus, it is counter-productive to acquiring wisdom for dealing with natural disasters.

Text-Mining in Long-Term Care: Exploring the Usefulness of Computer-Aided Analyzing Methods

In nursing homes, narrative data are collected to evaluate quality of care as perceived by residents or their family members. This results in a large amount of textual data which exceeds the capability of humans to analyse it. This study aims to explore the usefulness of text-mining approaches regarding narrative data gathered in a nursing home setting. Data has been collected as part of the project ‘Connecting Conversations’: assessing experienced quality of care by conducting individual interviews (n=125) with residents of nursing homes, family members and care professionals. Several pre-processing steps were applied to the textual data. Finally, a variety of text-mining analyses were conducted: individual and bigram word frequencies, correlation analysis and sentiment analysis. A survey was conducted to establish a sentiment analysis model tailored to text collected in long-term care for older adults. Residents, family members and care professionals uttered respectively 285, 362 and 549 words per interview. Word frequency analysis showed that words that occurred most frequently in the interviews are often positive. Although there are some differences in wording such as the use of ‘mother’ and ‘breakfast’, correlation analysis displayed that similar words are used by all three groups to describe quality of care. The majority of interviews displayed a neutral sentiment. Care professionals are more diverse in their sentiment than residents and family members: while some express a more positive sentiment, others express more negativity. This study demonstrates the usefulness of text-mining to extend our knowledge regarding quality of care in a nursing home setting.

The rise and fall of rationality in language

The surge of post-truth political argumentation suggests that we are living in a special historical period when it comes to the balance between emotion and reasoning. To explore if this is indeed the case, we analyze language in millions of books covering the period from 1850 to 2019 represented in Google nGram data. We show that the use of words associated with rationality, such as "determine" and "conclusion," rose systematically after 1850, while words related to human experience such as "feel" and "believe" declined. This pattern reversed over the past decades, paralleled by a shift from a collectivistic to an individualistic focus as reflected, among other things, by the ratio of singular to plural pronouns such as "I"/"we" and "he"/"they." Interpreting this synchronous sea change in book language remains challenging. However, as we show, the nature of this reversal occurs in fiction as well as nonfiction. Moreover, the pattern of change in the ratio between sentiment and rationality flag words since 1850 also occurs in New York Times articles, suggesting that it is not an artifact of the book corpora we analyzed. Finally, we show that word trends in books parallel trends in corresponding Google search terms, supporting the idea that changes in book language do in part reflect changes in interest. All in all, our results suggest that over the past decades, there has been a marked shift in public interest from the collective to the individual, and from rationality toward emotion.

Aspect-based Sentiment Analysis using Dependency Parsing

In this paper, an aspect-based Sentiment Analysis (SA) system for Hindi is presented. The proposed system assigns a separate sentiment towards the different aspects of a sentence as well as it evaluates the overall sentiment expressed in a sentence. In this work, Hindi Dependency Parser (HDP) is used to determine the association between an aspect word and a sentiment word (using Hindi SentiWordNet) and works on the idea that closely connected words come together to express a sentiment about a certain aspect. By generating a dependency graph, the system assigns the sentiment to an aspect having a minimum distance between them and computes the overall polarity of the sentence. The system achieves an accuracy of 83.2% on a corpus of movie reviews and its results are compared with baselines as well as existing works on SA. From the results, it has been observed that the proposed system has the potential to be used in emerging applications like SA of product reviews, social media analysis, etc.

Emotions explain differences in the diffusion of true vs. false social media rumors

False rumors (often termed “fake news”) on social media pose a significant threat to modern societies. However, potential reasons for the widespread diffusion of false rumors have been underexplored. In this work, we analyze whether sentiment words, as well as different emotional words, in social media content explain differences in the spread of true vs. false rumors. For this purpose, we collected {varvec{N}} =126{,}301 rumor cascades from Twitter, comprising more than 4.5 million retweets that have been fact-checked for veracity. We then categorized the language in social media content to (1) sentiment (i.e., positive vs. negative) and (2) eight basic emotions (i. e., anger, anticipation, disgust, fear, joy, trust, sadness, and surprise). We find that sentiment and basic emotions explain differences in the structural properties of true vs. false rumor cascades. False rumors (as compared to true rumors) are more likely to go viral if they convey a higher proportion of terms associated with a positive sentiment. Further, false rumors are viral when embedding emotional words classified as trust, anticipation, or anger. All else being equal, false rumors conveying one standard deviation more positive sentiment have a 37.58% longer lifetime and reach 61.44% more users. Our findings offer insights into how true vs. false rumors spread and highlight the importance of managing emotions in social media content.

Corpus based sentimenal movie review analysis using auto encoder convolutional neural network

In natural language processing, most prominent branch is sentiment analysis. People’s emotions and attitudes are analyzed using this sentiment analysis towards service, some product, etc. In prediction of the future scope of a product, some benefits are given by sentiment analysis. However, manual analysis of such a huge amount of documents is a highly tedious task, especially with limited time. Hence, for solving this problem, various attempts are made in literature and proposed different sentiment analysis methods. However, in generation of lexicon, popular NLP tools has some drawbacks. The accuracy of lexicons based on humans is less and they are limited too. On the other hand, lexicons based on dictionary are highly general and they are domain specific. So, a technique called Corpus Integrated Autoencoder Convolutional Neural Network based Sentiment Analysis (CI-AECNN) is proposed in this work for solving this issue. The sentiment lexicon generation based on corpus is performed in this work. Candidates sentiment orientation are computed using this and seed lexicon are added with recognized sentiment words and from seed lexicon, words with incorrect sentiment are removed. The long short-term memory (LSTM) is used for performing Word Sense Disambiguation. Conditional random fields are used for extracting features. At last, auto-encoder, convolutional neural network is used for performing classification. In MATLAB simulation environment, conducted this research work’s overall analysis and it indicates that better results are produced by proposed technique when compared with available techniques.

Explainable neural network-based approach to Kano categorisation of product features from online reviews

ABSTRACT The Kano model is an extensively used technique for understanding different types of customer preferences. It classifies product features based on the effects of their performance on the overall customer satisfaction. Compared to surveys, numerous online reviews can be easily collected at a lower cost. This paper proposes an explainable neural network-based approach for the Kano categorisation of product features from online reviews. First, product feature words are identified by clustering nouns based on word embedding. Subsequently, the sentiments of the product feature words are determined by conducting the Vader sentiment analysis. Finally, the effects of the sentiments of each product feature on the star rating are estimated using explainable neural networks. Based on their effects, the product features are classified into the Kano categories. A case study of three Fitbit models is performed to validate the proposed approach. The Kano categorisation by the proposed approach is compared with the results of a previous product feature word clustering and ensemble neural network-based method. The results exhibit that the former presents a more reliable performance than the latter. The proposed approach is automated after providing several hyperparameters and can assist companies in conducting the Kano analysis with increased speed and efficiency.

Contextual sentiment embeddings via bi-directional GRU language model

Compared with conventional word embeddings, sentiment embeddings can distinguish words with similar contexts but opposite sentiment. They can be used to incorporate sentiment information from labeled corpora or lexicons by either end-to-end training or sentiment refinement. However, these methods present two major limitations. First, traditional approaches provide a fixed representation to each word but ignore the alternation of word meaning in different contexts. As a result, the polarity of a certain emotional word may vary with context, but will be assigned with a same representation. Another problem is the handling of out-of-vocabulary (OOV) or informal-writing sentiment words that would be assigned generic vectors (e.g., <UNK>). In addition, if affective words are not included in affective corpora or lexicons, they would be treated as neutral. Using such low-quality embeddings for building a neural model will reduce performance. This study proposes a training model of contextual sentiment embeddings. A stacked two-layer GRU model was used as the language model, simultaneously trained to incorporate semantic and sentiment information from labeled corpora and lexicons. To deal with OOV or informal-writing sentiment words, the WordPiece tokenizer was used to divide the text into subwords. The resulting model can be transferred to downstream applications by either feature extractor or fine-tuning. The results show that the proposed model can handle unseen or informal writing sentiment words and thus outperforms previously proposed methods.

Application of Thematic Context-Based Deep Learning in Foreign Language Teaching

Foreign language teaching is not simply the transfer of knowledge, but rather the placement of students in contexts to explore and discover problems. The thematic contexts do not exist in isolation. Teachers should adopt certain teaching strategies based on thematic contexts, rely on relevant discourse, study the discourse text, and use rich learning and activities as the driving force to highlight students’ active experience and emotional experience. In this paper, we propose an ELT (English Language Teaching) affective analysis method based on contextual classification and genetic algorithms. The method first constructs ELT topic sets and ELT topic word sets using the LDA (latent Dirichlet allocation) model, then applies genetic algorithms to each ELT topic word set one by one using ELT label data to automatically iterate the sentiment values of words in the word sets, and finally calculates the sentiment polarity of ELT texts using the sentiment values of words in the word sets. The experimental results show that the accuracy of this method improves 3.12% compared with LDA, the recall rate reaches 87.32%, and F1 reaches 73.79%, which can obtain ELT sentiment information from contextual and nonfeatured sentiment words and effectively improve the accuracy of sentiment classification.

Improving sentiment analysis accuracy with emoji embedding

Due to the diversity and variability of Chinese syntax and semantics, accurately identifying and distinguishing individual emotions from online texts is challenging. To overcome this limitation, we incorporate a new source of individual sentiment, emojis, which contain thousands of graphic symbols and are increasingly being used for expressing emotion in online conversations. We examined popular sentiment analysis algorithms, including rule-based and classification algorithms, to evaluate the impact of supplementing emojis as additional features to improve the algorithm performance. Emojis were also translated into corresponding sentiment words when constructing features for comparison with those directly generated from emoji label words. In addition, considering different functions of emojis in texts, we classified all posts in the dataset by their emoji usage and examined the changes in algorithm performance. We found that emojis are effective as expanding features for improving the accuracy of sentiment analysis algorithms, and the algorithm performance can be further increased by taking different emoji usages into consideration. In this study, we developed an improved emoji-embedding model based on Bi-LSTM (namely, CEmo-LSTM), which achieves the highest accuracy (around 0.95) when analyzing online Chinese texts. We applied the CEmo-LSTM algorithm to a large dataset collected from Weibo from December 1, 2019 to March 20, 2020 to understand the sentiment evolution of online users during the COVID-19 pandemic. We found that the pandemic remarkably impacted individual sentiments and caused more passive emotions (e.g., horror and sadness). Our novel emoji-embedding algorithm creatively combined emojis as well as emoji usage with the sentiment analysis model and can handle emotion mining tasks more effectively and efficiently.

Measuring Customer Satisfaction With the University Front Line Services Using Association Rules

Customer satisfaction and quality services are among the global issues plaguing organizations. This study aimed at finding words/word patterns on comments and/or feedback from Facebook pages on the services provided by the frontline services of PSU-Urdaneta City campus to measure customer satisfaction by utilizing linguistics-based pattern recognition approach. This study employed association rules using the frequent-pattern growth (FP-growth), which adopts a divide-and-conquer strategy for finding frequent item sets. Meaningful patterns of negative comments on the services provided by some of the offices implying unsatisfactory customer service were revealed. However, there were also positive and satisfactory customer services provided by various offices as evidenced by positive comments addressed to the quality of rendered services. The result implies that sentiment analysis and word association can be utilized to measure customer satisfaction and serve as a tool to enrich and improve the frontline services provided by the institution to their clientele.

A data processing method based on sequence labeling and syntactic analysis for extracting new sentiment words from product reviews

A data processing method based on sequence labeling and syntactic analysis for extracting new sentiment words from product reviews

Multiplex network embedding for implicit sentiment analysis

As one of the hot research directions in natural language processing, sentiment analysis has received continuous and extensive attention. Different from explicit sentiment words indicating sentiment polarity, implicit sentiment analysis is a more challenging problem due to the lack of sentiment words, which makes it inadequate to use traditional sentiment analysis method to judge the polarity of implicit sentiment. This paper takes sentiment analysis as a special sign link prediction problem, which is different from traditional text-based method. In particular, by performing the word graph-based text level information embedding and heterogeneous social network information embedding (i.e. user social relationship network embedding, and user-entity sentiment network embedding), the proposed scheme learns the highly nonlinear representations of network nodes, explores early fusion method to combine the strength of these two types of embedding modeling, optimizes all parameters simultaneously and creates enhanced context representations, leading to better capture of implicit sentiment polarity. The proposed method has been examined on real-world dataset, for implicit sentiment link prediction task. The experimental results demonstrate that the proposed method outperforms state-of-the-art schemes, including LINE, node2vec, and SDNE, by 20.2%, 19.8%, and 14.0%, respectively, on accuracy, and achieves at least 14% gains on AUROC. For sentiment analysis accuracy, the proposed method achieves AUROC of 80.6% and accuracy of 78.3%, which is at least 31% better than other models. This work can provide useful guidance on the implicit sentiment analysis.

Adversarial neural network with sentiment-aware attention for detecting adverse drug reactions

Adverse drug reaction (ADR) detection is an important issue in drug safety. ADRs are health threats caused by medication. Identifying ADRs in a timely manner can reduce harm to patients and can also assist doctors in the rational use of drugs. Many studies have investigated potential ADRs based on social media due to the openness and timeliness of this resource; however, they have ignored the fine-grained emotional expression in social media text. In addition, the benchmark datasets from social media are usually small, which can result in the problem of over-fitting. In this paper, we propose the Adversarial Neural Network with Sentiment-aware Attention (ANNSA) model, which enhances the sentimental element in social media and improves the performance of neural networks via data augmentation. Specifically, a sentiment-aware attention mechanism is proposed to extract the word-level sentiment features associated with sentiment words and learn task-related information by optimizing a task-specific loss. For low-resource datasets, we use an adversarial training approach to generate perturbations of the word embeddings via an implicit regularization technique. ANNSA was tested on three social media ADR detection datasets, namely, Twitter, TwiMed (Twitter) and CADEC. The experimental results indicated the ability to achieve F1 values of 48.84%, 64.18% and 83.06%, respectively, comparable to the best results reported for state-of-the-art methods. Our study demonstrates that sentiment words are highly correlated with ADRs and that word-level sentiment features can assist in detecting ADRs from social media datasets.