Sentiment Score Research Articles

Content analysis of Chinese cities’ Five-Year Plan transport policy documents

Chinese cities’ Five-Year Plans establish the direction and priorities for their urban transport systems for the subsequent half-decade. In this study, we compiled and then analyzed the document structure and content of the Five-Year Plans for Transport for 23 Chinese cities at two points in time (2010 and 2020). These documents afford a unique opportunity to establish how Chinese transport policies vary across different types of cities during a period of rapid economic growth and transport network development. Using content analysis techniques, we report findings regarding frequency and sentiment (positive/negative) towards a set of traditional and emerging transport planning topics, as well as document legibility (words per sentence, sentences per paragraph, use of graphical content, etc.). Our findings indicate that compared to many western Regional Transport Plans, Chinese Five-Year Plans tend to be more text-heavy than similar documents in western countries, with their length increasing during the 2010s. Furthermore, we demonstrate systematic variability in terms of topic frequencies with respect to cities’ characteristics during the period 2010 to 2020, however the variations in terms of sentiment scores are weaker. More economically advanced cities exhibited a heightened focus on sustainable travel options, negative externalities related to cars, emerging technologies, and equity, whereas less economically developed cities emphasized regional development issues. We also demonstrate an increased focus over time on equity, vehicle technology, and parcel-delivery logistics within the Five-Year Plans. Of the various topics we analyzed, air pollution experienced the greatest decrease over time in sentiment.

Evaluating the Applicability of Existing Lexicon-Based Sentiment Analysis Techniques on Family Medicine Resident Feedback Field Notes: Retrospective Cohort Study.

Field notes, a form for resident-preceptor clinical encounter feedback, are widely adopted across Canadian medical residency training programs for documenting residents' performance. This process generates a sizeable cumulative collection of feedback text, which is difficult for medical education faculty to navigate. As sentiment analysis is a subfield of text mining that can efficiently synthesize the polarity of a text collection, sentiment analysis may serve as an innovative solution. This study aimed to examine the feasibility and utility of sentiment analysis using 3 popular sentiment lexicons on medical resident field notes. We used a retrospective cohort design, curating text data from University of Toronto medical resident field notes gathered over 2 years (from July 2019 to June 2021). Lexicon-based sentiment analysis was applied using 3 standardized dictionaries, modified by removing ambiguous words as determined by a medical subject matter expert. Our modified lexicons assigned words from the text data a sentiment score, and we aggregated the word-level scores to a document-level polarity score. Agreement between dictionaries was assessed, and the document-level polarity was correlated with the overall preceptor rating of the clinical encounter under assessment. Across the 3 original dictionaries, approximately a third of labeled words in our field note corpus were deemed ambiguous and were removed to create modified dictionaries. Across the 3 modified dictionaries, the mean sentiment for the "Strengths" section of the field notes was mildly positive, while it was slightly less positive in the "Areas of Improvement" section. We observed reasonable agreement between dictionaries for sentiment scores in both field note sections. Overall, the proportion of positively labeled documents increased with the overall preceptor rating, and the proportion of negatively labeled documents decreased with the overall preceptor rating. Applying sentiment analysis to systematically analyze field notes is feasible. However, the applicability of existing lexicons is limited in the medical setting, even after the removal of ambiguous words. Limited applicability warrants the need to generate new dictionaries specific to the medical education context. Additionally, aspect-based sentiment analysis may be applied to navigate the more nuanced structure of texts when identifying sentiments. Ultimately, this will allow for more robust inferences to discover opportunities for improving resident teaching curriculums.

Design of a User Comment Management System Based on Text Mining

Presently, text mining in e-commerce reviews predominantly focus on singular sentiment analysis, yet constraints persist in sentiment score computation, semantic inclination discernment, and lexicon construction. To address these limitations, this study establishes an e-commerce user comment management system based on text mining. It performs part-of-speech tagging and dependency grammar analysis on the historical corpus of e-commerce, unveiling collocations that potentially convey users' emotive predispositions. Subsequently, a dependency grammar rule table is formulated for the extraction of emotional words. The enhanced BiGRU model is employed for bidirectional extraction of textual features, which are subsequently fused with the TextCNN model. Test results evince that the system effectively accomplishes the desired objectives, with positive comments attaining accuracy and recall rates of 93.49% and 96.98%, respectively, thereby mitigating the drawbacks associated with laborious operations and inadequate precision inherent in extant e-commerce comment analysis systems.

Development of a model and method for hospice quality assessment from natural language processing (NLP) analysis of online caregiver reviews.

With a fraction of hospices having their Consumer Assessment of Healthcare Providers and Systems (CAHPS®) scores on Hospice Compare, a significant reservoir of hospice quality data remains in online caregiver reviews. The purpose of this study was to develop a method and model of hospice quality assessment from caregiver reviews using Watson's carative model. Retrospective mixed methods of pilot qualitative thematic analysis and sentiment analysis using NLP of Google and Yelp caregiver reviews between 2013 and 2023. We employed stratified sampling, weighted according to hospice size, to emulate the daily census of enrollees across the United States. Sentiment analysis was performed (n=3393) using Google NLP. Two themes with the highest prevalence had moderately positive sentiments (S): Caring staff (+.47) and Care quality, comfort and cleanliness (+.41). Other positive sentiment scores with high prevalence were Gratitude and thanks (+.81), "Treating the patient with respect" (+.54), and "Emotional, spiritual, bereavement support" (+.60). Lowest sentiment scores were "Insurance, administrative or billing" (-.37), "Lack of staffing" (-.32), and "Communication with the family" (-.01). In the developed quality model, caregivers recommended hospices with caring staff, providing quality care, responsive to requests, and offering family support, including bereavement care. All ten Watson's carative factors and all eight CAHPS measures were presented in the discovered review themes of the quality model. Close-ended CAHPS scores and open-ended online reviews have substantial conceptual overlap and complementary insights. Future hospice quality research should explore caregiver expectations and compare review themes by profit status.

Measuring and Understanding Crowdturfing in the App Store

Application marketplaces collect ratings and reviews from users to provide references for other consumers. Many crowdturfing activities abuse user reviews to manipulate the reputation of an app and mislead other consumers. To understand and improve the ecosystem of reviews in the app market, we investigate the existence of crowdturfing based on the App Store. This paper reports a measurement study of crowdturfing and its reviews in the App Store. We use a sliding window to obtain the relationship graph between users and the community detection method to binary classify the detected communities. Then, we measure and analyze the crowdturfing obtained from the classification and compare them with genuine users. We analyze several features of crowdturfing, such as ratings, sentiment scores, text similarity, and common words. We also investigate which apps crowdturfing often appears in and reveal their role in app ranking. These insights are used as features in machine learning models, and the results show that they can effectively train classifiers and detect crowdturfing reviews with an accuracy of up to 98.13%. This study reveals malicious crowdfunding practices in the App Store and helps to strengthen the review security of app marketplaces.

Understanding Antecedents That Affect Customer Evaluations of Head-Mounted Display VR Devices through Text Mining and Deep Neural Network

Although the market for Head-Mounted Display Virtual Reality (HMD VR) devices has been growing along with the metaverse trend, the product has not been as widespread as initially expected. As each user has different purposes for use and prefers different features, various factors are expected to influence customer evaluations. Therefore, the present study aims to: (1) analyze customer reviews of hands-on HMD VR devices, provided with new user experience (UX), using text mining, and artificial neural network techniques; (2) comprehensively examine variables that affect user evaluations of VR devices; and (3) suggest major implications for the future development of VR devices. The research procedure consisted of four steps. First, customer reviews on HMD VR devices were collected from Amazon.com. Second, candidate variables were selected based on a literature review, and sentiment scores were extracted. Third, variables were determined through topic modeling, in-depth interviews, and a review of previous studies. Fourth, an artificial neural network analysis was performed by setting customer evaluation as a dependent variable, and the influence of each variable was checked through feature importance. The results indicate that feature importance can be derived from variables, and actionable implications can be identified, unlike in general sentiment analysis.

Investigating the Role of Nutrition in Enhancing Immunity During the COVID-19 Pandemic: Twitter Text-Mining Analysis.

The COVID-19 pandemic has brought to the spotlight the critical role played by a balanced and healthy diet in bolstering the human immune system. There is burgeoning interest in nutrition-related information on social media platforms like Twitter. There is a critical need to assess and understand public opinion, attitudes, and sentiments toward nutrition-related information shared on Twitter. This study uses text mining to analyze nutrition-related messages on Twitter to identify and analyze how the general public perceives various food groups and diets for improving immunity to the SARS-CoV-2 virus. We gathered 71,178 nutrition-related tweets that were posted between January 01, 2020, and September 30, 2020. The Correlated Explanation text mining algorithm was used to identify frequently discussed topics that users mentioned as contributing to immunity building against SARS-CoV-2. We assessed the relative importance of these topics and performed a sentiment analysis. We also qualitatively examined the tweets to gain a closer understanding of nutrition-related topics and food groups. Text-mining yielded 10 topics that users discussed frequently on Twitter, viz proteins, whole grains, fruits, vegetables, dairy-related, spices and herbs, fluids, supplements, avoidable foods, and specialty diets. Supplements were the most frequently discussed topic (23,913/71,178, 33.6%) with a higher proportion (20,935/23,913, 87.75%) exhibiting a positive sentiment with a score of 0.41. Consuming fluids (17,685/71,178, 24.85%) and fruits (14,807/71,178, 20.80%) were the second and third most frequent topics with favorable, positive sentiments. Spices and herbs (8719/71,178, 12.25%) and avoidable foods (8619/71,178, 12.11%) were also frequently discussed. Negative sentiments were observed for a higher proportion of avoidable foods (7627/8619, 84.31%) with a sentiment score of -0.39. This study identified 10 important food groups and associated sentiments that users discussed as a means to improve immunity. Our findings can help dieticians and nutritionists to frame appropriate interventions and diet programs.

Benefits of Adopting Wild Pedagogies in University Education

Several studies have demonstrated the positive impact of wild pedagogies on the well-being and learning of primary learners. However, wild pedagogies in higher education remain relatively obscure. This study assesses whether wild pedagogies affect the wellness of university students and analyzes the outcomes of the natural learning experiences in a higher education setting. As such, we use the roBERTa model to evaluate the sentiment score and thematic content to analyze 167 reflective essays on conducted natural learning experiences by undergraduate engineering students from a large Canadian public university. Our findings indicate that wild pedagogies benefit the wellness of university students and provide positive learning experiences. Moreover, positive natural learning experiences motivate students to develop environmental consciousness and sentimental connections with nature.

The Role of Climate Change News in Pharma Industry

Abstract In this article, we aim to study the role of climate change news in the European Big-Pharma companies returns. The goal of the research is to explain if the sentiment of the news posted on Twitter can explain the market movements, even if current global events may affect stock prices. The previous literature reveals the impact of climate change in the economy, but in the field of pharma companies, there is less information of how climate change affects the evolution in the stock market. We used the VADER methodology to examine and analyze the climate change news posted on Twitter. This allows us to extract the sentiment and use it to study the dependence between sentiment score and the evolution of the European Big-Pharma companies. To examine the relation, we use Ordinary Least Squares regressions and Quantile Regression. Our results reveal the fact that there is no significant dependency between the sentiment score of the news published on Twitter by the biggest newspapers and the price increase of the European Pharma companies stocks. We observe a small increase in dependence when we use the sentiment score with 1 day lag in the Ordinary Least Squares regressions and another improvement in results with Quantile Regression.

Count Me Too: Sentiment Analysis of Roman Sindhi Script

Social media has given voice to people around the globe. However, all voices are not counted due to the scarcity of lexical computational resources. Such resources could harness the torrent of social media text data. Computational resources for rich languages such as English are available. More are being developed, meanwhile strengthening and enhancing the current ones. However, Roman Sindhi, a resource-poor writing style, is a phonetically rich language lacking computational resources, creating a working space for researchers. This work attempts to develop lexical sentiment resources that will help calculate the public opinion expressed in Roman Sindhi and bring their point of view into the limelight. This work is one of the initial efforts to develop lexical Roman Sindhi sentiment dictionary resources to help detect sentiment orientation in a text. Furthermore, it also developed two interfaces to leverage the lexical resources—a Roman Sindhi to English translator (RoSET) that translates a Roman Sindhi feature into an equivalent English word and a Roman Sindhi rule-based sentiment scorer ( RBRS3) that assigns sentiment score to a Roman Sindhi script features. The results obtained from the developed system accommodated the bilingual dataset (Roman Sindhi + English) more adequately. An increase of 20.8% was recorded for positive sentence detection, and a 16% increase was obtained for negative sentences, whereas neutral sentences were marginalized to a lower number (59.31% decrease). The resultant system makes those public voices expressed in the Roman Sindhi script get counted, which otherwise are in vain.

Do linguistic features of research article titles affect received online attention? A corpus-based analysis

Purpose Scientific impact is traditionally assessed with citation-based metrics. Recently, altmetric indices have been introduced to measure scientific impact both within academia and among the general public. However, little research has investigated the association between the linguistic features of research article titles and received online attention. To address this issue, the authors examined in the present study the relationship between a series of title features and altmetric attention scores.Design/methodology/approach The data included 8,658 titles of Science articles. The authors extracted six features from the title corpus (i.e. mean word length, lexical sophistication, lexical density, title length, syntactic dependency length and sentiment score). The authors performed Spearman’s rank analyses to analyze the correlations between these features and online impact. The authors then conducted a stepwise backward multiple regression to identify predictors for the articles' online impact.Findings The correlation analyses revealed weak but significant correlations between all six title features and the altmetric attention scores. The regression analysis showed that four linguistic features of titles (mean word length, lexical sophistication, title length and sentiment score) have modest predictive effects on the online impact of research articles.Originality/value In the internet era with the widespread use of social media and online platforms, it is becoming increasingly important for researchers to adapt to the changing context of research evaluation. This study identifies several linguistic features that deserve scholars’ attention in the writing of article titles. It also has practical implications for academic administrators and pedagogical implications for instructors of academic writing courses.

The Role of Country-pair-related News Sentiment in Foreign Exchange

This article explores the relative, explanatory contribution of country-pair-related political and financial news to foreign exchange rates. Contributing political factors are measured through the sentiment scores of published news while contributing financial factors are measured through various economic indicators such as price and volume of USD and CNY oil futures, the Russian IMOEX Index, and corresponding interest differentials. The results show that news sentiment plays a minor role in exchange rate determination while other factors such as prices and traded volumes in oil future contracts and interest differentials are significant contributing factors to the exchange rate determination. Nevertheless, the quality and quantity of news coverage of geo-political or economic events seems to play an important role when it comes to the impact of news on exchange rates. Among the sentiment-analyzed currency pairs, EUR/USD exhibits by far the highest sensitivity to political and economic news, followed by EUR/RUB, RUB/CNY, EUR/CNY, USD/CNY, and USD/RUB. Keywords: foreign exchange, news sentiment analysis, text mining, geo-political sentiment JEL-Codes: F31, E71

Negotiations to implement area-based management tools beyond national jurisdiction: the scientific community’s view

A new international legally-binding instrument, under the United Nations Convention on the Law of the Seas (UNCLOS), for the conservation and sustainable use of marine biodiversity in areas beyond national jurisdiction has recently been agreed on– the BBNJ agreement. Area-based management tools (ABMTs), including marine protected areas (MPAs) have an important role in maintaining biodiversity and ecosystem services in the current context of multiple threats to the ocean and are one of central elements of new instrument. In this work, we assessed the perspective of the scientific community, throughout the period of negotiations, on the potential of the BBNJ treaty to promote the creation of new area-based management tools, including MPAs, and fulfil acknowledged gaps in ocean governance. A systematic literature review was conducted, resulting in 80 publications then analysed in detail. From these, a total of 608 key messages were retrieved and classified into: 1) Strengths (S), Weaknesses (W), Opportunities (O) or Threats (T) for a SWOT analysis and 2) one of six categories that cover crucial aspects for the successful implementation of the ABMTs in areas beyond national jurisdiction. A Sentiment Analysis (SA) to these key messages shows that the instrument has been perceived by the scientific community as an opportunity for conserving and achieving sustainable use of biodiversity. However, the scientific community also feels that agreement needs stronger provisions to ensure effective measures, which is reflected by the small number of identified strengths. An overall decrease in sentiment score over the negotiations period, i.e. a growing pessimism, was also observed, which is supported by an increase of weaknesses and threats identified in the final stages of the negotiations. Our results suggest that despite its potential to promote conservation in areas beyond national jurisdiction, the instrument should include a unified definition of MPA, address fishing activities and clarify conflicting terms in its provisions, such as the term “not undermine”. Further, we show that sentiment analysis is a useful tool to evaluate opinion trends and facilitate the integration of different and subjective perspectives into final provisions of complex social-political-environmental agreements, identifying positive and negative attitudes that can enable better solutions to address existing governance challenges in international waters.

Superposition effect of online news on fintech platforms

PurposeThe rise of the mobile Internet has accumulated much text information in various online financial forums. Such information often contains the emotional attitudes of investors toward financial technology (fintech) platforms, so extracting the sentimental tendency information has great practical value for the development of fintech platforms. Based on the investor sentiment theory, the paper aims to analyze the relevant social media data and test the influence path of online news evaluation on the stock price fluctuation of fintech platforms.Design/methodology/approachTaking Oriental Fortune as the research object, this paper selects multiple variables such as stock bar popularity, snowball popularity, news popularity and news sentiment scores collected by UQER and combines the sentiment scores of single daily news into a daily sentiment score. Based on the period from November 1, 2019 to March 31, 2020, during the emergence of the coronavirus disease 2019 (COVID-19) pandemic as the background, the authors conduct the Granger causality test based on the vector autoregressive (VAR) model and analyze the relevant evaluation of Oriental Fortune through the empirical model.FindingsThe authors' results show that different online evaluations impact the rise and fall of stock prices differently, while news popularity has the most significant impact. Besides, news sentiment scores on share price fluctuation have a relatively substantial influence. These findings indicate that the authoritative news evaluation can strongly guide investors to make relevant investment behavior operations in the information dissemination process, significantly affecting stock prices.Originality/valueThe research findings of this paper have good inspiration and reference values for investors and financial regulators.

A sentiment analysis on online psychiatrist reviews to identify clinical attributes of psychiatrists that shape the therapeutic alliance.

While online reviews from physician rating websites are increasingly utilized by healthcare providers to better understand patient needs, it remains difficult to objectively identify areas for improvement in providing psychiatric care. To quantitatively characterize the sentiment of online written reviews of psychiatrists to determine clinical attributes that can be strengthened to improve psychiatrists' therapeutic alliance with their patients. Sentiment scores of 6,400 written reviews of 400 US-based psychiatrists on a US-based online physician rating website were obtained through a natural-language-processing-based sentiment analysis. Relationships among sentiment scores, average star ratings, and demographics were examined. Linguistic analyses determined words and bigrams that were highly associated with reviews with the most positive and negative sentiment. Sentiment scores were significantly correlated with average star ratings of the psychiatrists (R = 0.737, p < 0.001). Psychiatrists who were younger (< 56 years old) and/or practiced in the Northeast had significantly higher average star ratings than those older and/or practicing in the Southwest. Frequency analysis showed that positive reviews most frequently contained "time" (N = 1,138) and "caring" (N = 784) while negative reviews most frequently contained "medication" (N = 495) and "time" (N = 379). Logistic regression analysis revealed that reviews were more likely to be considered positive when they included "great listener" (OR = 16.89) and "comfortable" (OR = 10.72) and more likely to be negative when they included "meds" (OR = 0.55) and "side effect" (OR = 0.59). Psychiatrists who are younger and located in the Northeast receive more positive reviews; there may be potential for demographic bias among patient reviewers. Patients positively rate psychiatrists who make them feel heard and comfortable but negatively rate encounters centered around medications and their side effects. Our study lends quantitative evidence to support the importance of thorough and empathetic communication of psychiatrists in building a strong therapeutic alliance.

Deep learning model with sentiment score and weekend effect in stock price prediction

Deep learning model with sentiment score and weekend effect in stock price prediction

Generating a Mental Health Curve for Monitoring Depression in Real Time by Incorporating Multimodal Feature Analysis Through Social Media Interactions

The coronavirus pandemic has led to a dramatic increase in depression cases worldwide. Several people are utilizing social media to share their depression or suicidal thoughts. Thus, the major goal of the proposed study is to examine Twitter posts by users and identify features that may indicate depressed symptoms among online users. A numerical metric for each user is proposed based on the sentiment value of their tweets, and it is demonstrated that this feature can detect depression with good accuracy by using several machine learning classifiers. The paper proposes a novel method for measuring the mental health index of an individual by combining the sentiment score with multimodal features extracted from his online activities. A real-time curve is generated using this index that can monitor a person's mental health in real time and offer real-time information about his state. The proposed model shows an accuracy of 89% using SVM, and proper feature selection is very essential for obtaining good performance.

Public sentiment towards cruises and resulting stock performance in 2017–2021

Social and economic impacts of the cruise industry are undeniable within the United States (U.S.). Online media about cruising was quantified in terms of volume and net sentiment, then analyzed alongside stock market performance of cruise companies. Daily net sentiment was positively correlated with daily stock closing prices for the three major operators studied (NCLH, RCL, CCL). Further analysis reveals that online media net sentiment had a positive effect on daily closing prices; an increase of 1 point in the sentiment score led to a $0.07, $0.23, and $0.08 increase in the daily closing price of NCLH, RCL, and CCL, respectively. In addition, imposing a no sail order led to negative impacts with the greatest against RCL. Finally, a variable for the COVID effect on these firms revealed differing magnitudes of effect and directionality to each of the firms.

Partisan US News Media Representations of Syrian Refugees

We investigate how representations of Syrian refugees (2011-2021) differ across US partisan news outlets. We analyze 47,388 articles from the online US media about Syrian refugees to detail differences in reporting between left- and right-leaning media. We use various NLP techniques to understand these differences. Our polarization and question answering results indicated that left-leaning media tended to represent refugees as child victims, welcome in the US, and right-leaning media cast refugees as Islamic terrorists. We noted similar results with our sentiment and offensive speech scores over time, which detail possibly unfavorable representations of refugees in right-leaning media. A strength of our work is how the different techniques we have applied validate each other. Based on our results, we provide several recommendations. Stakeholders may utilize our findings to intervene around refugee representations, and design communications campaigns that improve the way society sees refugees and possibly aid refugee outcomes.

Sentiment Analysis of E-commerce Product Review through Machine Learning

Sentiment analysis is a way which is used to determine that a piece of information is positive, negative or neutral. In the analysis of text or any kind of information natural language processing (NLP) and machine learning (ML) both are combined to assign sentiment scores to the topics, categories and any kind of entities within a given phrase. In today's day and time online shopping has become well received among the people. If we talk about ordinary people, they always think too much before buying any product through any e-commerce application. The trust of the people of e-commerce applications is not very high. So, people turn to reviews to fill this confidence gap. And to ensure this trust Sentiment Analysis were used. Our project can be a great option for people to maintain their trust. In this project we are analyzing products of respective e-commerce apps on the behalf of their reviews and ratings. Users will get information for each product whether it can be a good one or not on the basis of reviews and ratings. A great number of internet sources are present on categorical views of activities, goods and services, beliefs or perhaps the mind created by the online dwellers. In this fierce business world, various industries, especially e-commerce, exceptionally use sentiment analysis to increase productivity and make better business decisions. This project tackles a comprehensive overview of sentiment analysis and relevant techniques in the e-commerce sector that is always keen to find out about the consumers' opinions of their goods and services. It starts with the view of an assessment of sentiments that have come out as a method for understanding clients’ emotions.