Level Of Sentiment Research Articles

Can Herding Be Adaptive? Evidence from Markets Sentiment, News Sentiment and Happiness in Global Energy Markets

This study investigates the adaptive nature of herding behaviour in global energy markets, focusing on the USA, Europe and Asia, from January 2013 to December 2023. Utilizing advanced sentiment analysis tools, including Thomson Reuters MarketPsych Indices, Bloomberg Sentiment Analysis and the Hedonometer, this study captures real-time fluctuations in market mood. By employing Cross-Sectional Absolute Deviation models, static regression, rolling regression and quantile-on-quantile regression, this study examines the impact of investor sentiment, news sentiment and happiness on herding behaviour under varying market conditions. The findings revealed significant regional variations and underscored the dynamic and context-dependent aspects of herding behaviour. In the USA, higher levels of investor happiness and positive market sentiment are linked to increased herding behaviour, whereas negative news sentiment is linked to reduced herding behaviour. Similar but less pronounced patterns are observed in Europe, whereas Asian markets show weaker correlations, highlighting the critical role of market volatility and trading volume. These insights offer valuable implications for portfolio management, regulatory frameworks and investment strategies, thus enhancing the understanding of herding behaviour in volatile and sentiment-driven markets.

The advantages of lexicon-based sentiment analysis in an age of machine learning.

Assessing whether texts are positive or negative-sentiment analysis-has wide-ranging applications across many disciplines. Automated approaches make it possible to code near unlimited quantities of texts rapidly, replicably, and with high accuracy. Compared to machine learning and large language model (LLM) approaches, lexicon-based methods may sacrifice some in performance, but in exchange they provide generalizability and domain independence, while crucially offering the possibility of identifying gradations in sentiment. We demonstrate the strong performance of lexica using MultiLexScaled, an approach which averages valences across a number of widely-used general-purpose lexica. We validate it against benchmark datasets from a range of different domains, comparing performance against machine learning and LLM alternatives. In addition, we illustrate the value of identifying fine-grained sentiment levels by showing, in an analysis of pre- and post-9/11 British press coverage of Muslims, that binarized valence metrics give rise to different (and erroneous) conclusions about the nature of the post-9/11 shock as well as about differences between broadsheet and tabloid coverage. The code to apply MultiLexScaled is available online.

The Impact of Sentiment on Realized Higher-Order Moments in the S&P 500: Evidence from the Fear and Greed Index

This study empirically investigates the relationship between realized higher-order moments and the Fear and Greed Index as a measure of sentiments. We estimate daily realized moments using 5 min return data of the S&P 500 index from 3 January 2011 to 18 September 2020. We find that the Fear and Greed Index significantly impacts realized volatility during periods of extreme fear. Additionally, various sentiment indicators influence realized skewness and realized kurtosis. The VIX index significantly reduces realized skewness across all sentiment levels. Bearish and bullish sentiments have a significant negative relationship with negative realized skewness during periods of extreme fear and extreme greed. However, the Fear and Greed Index and bearish and bullish sentiments have a significant positive relationship with positive realized skewness. During extreme fear, the Fear and Greed Index and bearish and bullish sentiments have a significant negative relationship with realized kurtosis. These results remain consistent when considering the non-linear characteristics of the Fear and Greed Index during periods of extreme fear and extreme greed. These findings highlight the relevance of understanding sentiment in financial risk management and its significant relationship with the asymmetric and extremity characteristics of asset returns.

Sentiment analysis as an information agenda and public opinion research method (on the example of Chinese mass media and social networks)

The information agenda broadcast by Chinese media resources is a source of up-to-date data on public opinion on key issues of social welfare. Due to the technical peculiarities of the organization of Chinese websites and the need to attract additional resources for automatic processing (parsing) of texts in Chinese, this topic is not widely represented in domestic and foreign studies. The purpose of this paper is to demonstrate the methodology and results of public opinion estimation on the example of data collected from Chinese media and social networks based on a trained sentiment analysis model of Chinese text data. The ML model was used to comparatively analyze Chinese language content on urban infrastructure development issues for the period 2020–2022. The results are presented in the format of sentiment distribution charts based on media and social media data by month over a 2-year period. It is revealed that the level of sentiment differs significantly depending on the type of data source. A steady prevalence of positive sentiment in mass media and negative sentiment in social networks was determined, which can be explained by differences in the composition of text authors, restrictions imposed on the content published in the sources, as well as different purposes of resource use by users.

Examining extremist language use amongst Australian members of an online far-right forum

ABSTRACT Far-right extremists use the internet to recruit and connect with other radicalised individuals and spread their propaganda online, with them being prolific users of online forums and social media. Such online data can be analysed using linguistic tools to identify markers of radicalisation in social media, forum posts, and other extremist texts. Few studies have examined how language and sentiment online evolves in extremist forums, which provides insight into how radicalisation into extremism unfolds overtime. To address this gap, we examine how the extremist language used by Australian members of the online far-right forum Iron March changed in relation to the level of engagement on the forum, as well as assessing whether any relationship existed between online extremist sentiment and offline violence. Forum data were computationally coded and analysed using the Grievance Dictionary, which is designed to identify psycholinguistic indicators of extremism. Results indicate that while extremist language changes over time, there was no support for the suggestion that greater forum engagement results in higher levels of extremist sentiment. The results found that a high level of online extremist sentiment is associated with offline violence. Findings are linked to existing literature, and limitations in the study design are acknowledged.

Analysis of Online User Reviews for Popular Tourist Attractions: Almaty Case

Attractions in the tourism industry are one of the components that motivate tourists to visit destinations, such as entertainment, natural, cultural, and historical richness. For such reasons, people decide to visit unique destinations and spend time there. Almaty, the largest city of Kazakhstan, is one of the significant attraction centers of the Central Asia region, offering tourists unique and pleasant features with several tourist attractions. This study aims to analyze online user reviews of tourist attractions in Almaty, Kazakhstan, using machine learning and text mining methods. The primary focus is on identifying the main thematic clusters of reviews and their sentiment and comparing these themes with the types of attractions: historical, natural, and man-made. A total of 7,515 reviews were collected from the TripAdvisor website. The data was processed using sentiment analysis, topic modeling, and hierarchical clustering methods. The analysis revealed that 38% of the reviews were related to natural attractions, 34% to man-made, and 28% to historical ones. The most positive reviews were associated with natural attractions, while historical and man-made attractions received 79.38% and 81.40% positive reviews, respectively. In addition, the items that make up these attractions are identified, and their sentiment levels are pointed out. In addition to this situation, visitors have the most positive expressions for natural attractions, especially landscapes and lakes. The findings emphasize the importance of considering review themes to improve the quality of tourist services and to enhance the positive image of Almaty as a tourist destination.

Red, blue, and green? The association between CEOs' political ideologies and green new product introductions

AbstractNot all firms exhibit the same level of commitment to green new product introductions (GNPIs), yet our understanding of the factors underlying these disparities remains incomplete. Prior research has primarily focused on firm‐level factors, paying little attention to individual‐level antecedents of GNPIs. This imbalance in the GNPI literature contrasts with the broader innovation and general management literature, which displays an ever‐growing interest in the “human side of innovation,” acknowledging the relevance of Chief Executive Officers' (CEOs') political ideologies for organizational outcomes. Addressing this imbalance, our study examines the relationship between CEOs' political ideologies and their firms' GNPIs, along with the conditions that shape this influence. Grounded in social identity theory, our study first argues that the more liberal CEOs are, the more GNPIs their firms are likely to generate and that this association is amplified by CEO power. It then proposes that the more liberal CEOs are, the more likely they are to respond to adverse situations beyond their control (a Republican presidency or lower levels of consumer green sentiment) by initiating more GNPIs. It finally posits that the more liberal CEOs are, the fewer GNPIs they tend to initiate in response to adverse situations for which they are accountable (involvement in sustainability‐related scandals). We integrate data from seven databases into a longitudinal dataset comprising 89 firms and 192 CEOs over the period 2010–2020 to test our theoretical framework empirically. Time‐lagged panel regression analyses strongly support our theoretical arguments. Our findings contribute to the emergence of an individual‐level, microfoundational perspective on sustainable innovations, our knowledge about the organizational implications and boundary conditions of CEOs' political ideologies, and the treatment of multiple identities within social identity theory, especially the relationship between political and occupational identities. The implications of our findings extend to business practitioners, offering valuable insights for CEOs, boards of directors, and investors.

Preparing Teachers for Inclusive Education: Pre-Service Teachers’ Knowledge, Perceptions and Experiences of Inclusive Pedagogy from Teaching Practice

Various scholars have questioned the effectiveness of teacher education programmes in preparing teachers for inclusive education. This study examines how teacher education programmes prepare pre-service teachers for inclusive education in terms of perceptions, knowledge and pedagogy. The study uses focus group discussions to examine pre-service teachers’ knowledge of inclusive education and their experiences of inclusive pedagogy from teaching practice. The SACIE-R questionnaire tool assesses the perceptions of 187 pre-service teachers with regard to inclusive education. The findings indicate that pre-service teachers acquire theoretical knowledge with gaps in field-based knowledge that hinder their ability to link theory and practice, and to develop inclusive pedagogy. Moreover, pre-service teachers have a low level of sentiments and harbour many concerns and negative attitudes towards inclusive education. The findings of the study contribute insights that can inform the design and structuring of inclusive education courses in teacher education programmes.

Sentiment Analysis of Google Maps User Reviews on the Play Store Using Support Vector Machine and Latent Dirichlet Allocation Topic Modeling

These days, traveling is made easier by utilizing easily accessible online directions such as Google Maps. Google Maps provides real-time routes by displaying and presenting the closest routes that users can take. However, lately, the routes provided by Google Maps services often get users lost by presenting routes such as forests, narrow roads, and even dead ends. Therefore, this study aims to determine the level of user satisfaction and sentiment into two categories, namely positive and negative, based on reviews on the Google Play Store platform using the Support Vector Machine (SVM) algorithm and topic modeling using Latent Dirichlet Allocation (LDA) to find out the collection of topics that are the main topics of conversation by users regarding Google Maps services. The results of this study show that the SVM algorithm is feasible to use in sentiment analysis classification with an accuracy value of 86%, precision of 93%, recall of 53%, and f1-score of 52%. In addition, topic modeling is applied to generate coherence values for each topic, which shows that the higher the coherence value, the more specific the topic is. The highest coherence value generated in this study was two topic models with a coherence value of 35.15%, but this study took five with a coherence value of 33.39%. The five topic models to be applied in this study are selected because they have a good enough coherence value to identify the main topics and hidden topics in Google Maps user reviews with the Latent Dirichlet Allocation model. The topic model shows five aspects users often discuss: Google Maps route accuracy, system and service errors, navigation application directions, lost time history, and convoluted route provision.

Empirical insights into the interaction effects of groups at high risk of depression on online social platforms with NLP-based sentiment analysis

With the proliferation of digital technology and the increasing prevalence of social media, some users at high risk of depression have opted to seek solace, acceptance, and assistance in online communities. However, the extant research is deficient in terms of the segmentation of groups, particularly subcultural groups. By analyzing the “Super Hashtags” and “Tree Hole” groups on Sina Weibo from January to March 2023 using a crawler and the ERNIE 3.0-Base model for sentiment analysis, the study uncovers distinct sentiment profiles and interaction patterns, revealing significant correlations between interaction metrics and sentiment levels. The findings indicate that while there are no significant differences in sentiment levels between the two communities, the “Tree Hole” community exhibits greater sentiment variability. Moreover, the study identifies that interaction behaviors are closely linked to sentiment states, emphasizing the importance of understanding the complex dynamics between online interactions and mental well-being. These insights contribute to the development of more effective support mechanisms within online platforms for individuals at risk of depression.

From Tweets to Streets: Observational Study on the Association Between Twitter Sentiment and Anti-Asian Hate Crimes in New York City from 2019 to 2022.

Anti-Asian hate crimes escalated during the COVID-19 pandemic; however, limited research has explored the association between social media sentiment and hate crimes toward Asian communities. This study aims to investigate the relationship between Twitter (rebranded as X) sentiment data and the occurrence of anti-Asian hate crimes in New York City from 2019 to 2022, a period encompassing both before and during COVID-19 pandemic conditions. We used a hate crime dataset from the New York City Police Department. This dataset included detailed information on the occurrence of anti-Asian hate crimes at the police precinct level from 2019 to 2022. We used Twitter's application programming interface for Academic Research to collect a random 1% sample of publicly available Twitter data in New York State, including New York City, that included 1 or more of the selected Asian-related keywords and applied support vector machine to classify sentiment. We measured sentiment toward the Asian community using the rates of negative and positive sentiment expressed in tweets at the monthly level (N=48). We used negative binomial models to explore the associations between sentiment levels and the number of anti-Asian hate crimes in the same month. We further adjusted our models for confounders such as the unemployment rate and the emergence of the COVID-19 pandemic. As sensitivity analyses, we used distributed lag models to capture 1- to 2-month lag times. A point increase of 1% in negative sentiment rate toward the Asian community in the same month was associated with a 24% increase (incidence rate ratio [IRR] 1.24; 95% CI 1.07-1.44; P=.005) in the number of anti-Asian hate crimes. The association was slightly attenuated after adjusting for unemployment and COVID-19 emergence (ie, after March 2020; P=.008). The positive sentiment toward Asian tweets with a 0-month lag was associated with a 12% decrease (IRR 0.88; 95% CI 0.79-0.97; P=.002) in expected anti-Asian hate crimes in the same month, but the relationship was no longer significant after adjusting for the unemployment rate and the emergence of COVID-19 pandemic (P=.11). A higher negative sentiment level was associated with more hate crimes specifically targeting the Asian community in the same month. The findings highlight the importance of monitoring public sentiment to predict and potentially mitigate hate crimes against Asian individuals.

Inclusive Education: Typically Developing Student's Sentiments, Attitudes, and Concerns

Politeknik Negeri Jakarta (PNJ) is a prominent higher education institution in Indonesia that extends its educational services to students with special educational needs (SEN). However, the existing educational practices at PNJ exhibit a partial inclusivity model, whereby SEN students are segregated into separate classes and study programs distinct from their typically developing (TD) peers. The sentiments, attitudes, and concerns of TD students play a pivotal role in the overall success of inclusive education (IE) initiatives. This study seeks to investigate the above regarding IE within the context of PNJ. The study encompassed a sample of 400 students from PNJ, employing a quantitative methodology with a descriptive and correlational non-experimental approach. The results unveiled that a majority of the participants held a moderate level of sentiments, attitudes, and concerns toward inclusive education. Notably, factors such as direct contact with persons with disabilities (PwD), knowledge about PwD, and confidence levels in interacting with them emerged as influential determinants in shaping sentiments, attitudes, and concerns related to IE. This research offers valuable insights into the perceptions of TD students concerning IE at PNJ, which can inform policy recommendations aimed at enhancing educational provisions for SEN students. The findings underscore the importance of fostering a more inclusive and supportive educational environment, promoting positive attitudes, and addressing concerns to facilitate the successful implementation of inclusive education practices within the institution. Keywords: inclusive education, sentiments, attitudes, concerns, typically developing students, special educational needs students

Public Opinion in Conflict Situations: A Sentiment Analysis of Tweets About Russia During the War on Ukraine

ABSTRACT Wars not only bring death and suffering to the conflicting parties, but they can also trigger a spiral of negative emotions in the countries observing the conflict. This study examines global public opinion at the start of the invasion of Ukraine in 2022 by analyzing comments about Russia on X (formerly Twitter) in 127 countries. Using Python, the sentiment levels (positive, negative, neutral) of a total sample of 429,408 tweets in 48 languages were estimated. In addition to quantifying a net sentiment index for each country, the study focuses on the possible existence of differences in terms of military, political and cultural factors. The results show that sentiment towards Russia after the invasion was negative in most countries around the world, although there were significant differences between opinions in NATO countries and those allied with Russia. Additionally, public opinion was less negative in individualistic countries compared to those with collectivist societies.

A meta-analysis of international experience and performance: exploring the role of global mobility and national sentiments

PurposeInternational experience has long been recognized as a crucial determinant for firms’ knowledge management in the existing literature. However, within a global context, the relationship between international experience and the performance of multinational enterprises is intricate and remains ambiguous. While the impact of people mobility has been extensively studied, limited understanding exists regarding how global mobility of people and evolving external environments reshape the relationship. This study aims to integrate existing empirical evidence on this relationship and examines the contingencies posed by environmental factors.Design/methodology/approachThis study conducted a multilevel meta-analysis based on a sample of 231 effect sizes collected from 167 articles to systematically examine the international experience–performance relationship, considering the moderating effect of the global mobility of people and the rise of national sentiments (including authoritarianism and protectionism). A two-stage procedure comprising Hedges-Olkin-type meta-analysis and random-effects meta-analytic regression was adopted.FindingsThe findings demonstrate a predominantly positive international experience–performance relationship that varies across studies owing to differences in research design, variable measurements and firm characteristics. The relationship is positively moderated by the global mobility of people, yet the positive effect is contingent upon the level of national sentiments within home countries. The beneficial effect of inbound mobility on this relationship is attenuated by authoritarianism and protectionism, while the effect of outbound mobility is positively influenced by authoritarianism and less affected by protectionism.Originality/valueThis study offers novel theoretical insights into multinationals’ knowledge accumulation in the internationalization process. It contributes to the existing literature by presenting an integrated framework elucidating the international experience–performance relationship. Building upon the knowledge-based view, it integrates environmental dynamics and national sentiments to investigate the performance implications of multinationals’ international experience, thereby providing valuable practical insights for effective global knowledge management.

The Impression of Sustainable Fashion in Customers’ Mind

The research dives into customer perceptions of sustainable fashion and how it is impacting their decision to possibly make a purchase. With the currently evolving trends and increasing consciousness about our environment, people have started opting into more eco - friendly options in their daily life choices. Some of the options are clear but some need to be given more awareness to be implemented. Fashion has been something of that sort where people do not really look into much eco - friendly options and is ready for go for anything that gets them their “look” which delves into confidence and status that are some of the many things fashion provides them. The study has been an intersection of fashion and sustainability. The literature review shows the importance to eco - friendly materials embedded into fashion, technological innovations into the industry and a little about fair working conditions. The methodology involved a Likert Scale questionnaire consisting of 150 respondents who used different fashion brands. Results showed us a neutral overall sentiment level which signals an opportunity for marketers to explore better and create more awareness to drive customers into a purchase. Social media was a crucial response we received in terms of respondents agreeing how online media has helped them in creating more awareness about the sustainability in the fashion industry. This also gave a signal to marketers on more efficient communication strategies and how long term continuous improvements are necessary for a long term impact. They can get the most out of these findings to engage with the customers probably online and to shape an efficient sustainable fashion industry.

Strategi Social CRM Dalam Menangani Keluhan Pelanggan Pada Instagram Pos Indonesia

Every day, many customers submit complaints through the comment section on Pos Indonesia's main Instagram account (@posindonesia.ig). This study aims to understand how Pos Indonesia designs its Social CRM strategy to address customer complaints on the Instagram social media platform @posindonesia.ig. The theory employed in this research is the Social Media SOME model (Share, Optimize, Manage, Engage) developed by Luttrell (2018). A qualitative approach with descriptive research is utilized in this study. Data collection methods involve in-depth interviews, observation, and document analysis. The findings of this research reveal that the Social CRM Strategy implemented by Pos Indonesia's internal communication and contact center includes four main activities: (1) Share, where internal communication strives to reduce negative sentiment by paying attention to the content liked by followers, (2) Optimize, where internal communication focuses on educational content presented in a socializing format, (3) Manage, where internal communication monitors social media content to assess the level of impressions and sentiments from followers, and (4) Engage, where internal communication involves internal buzzers to provide positive comments with the hope that customers planning to express negative complaints will change their minds.

Migration sentiments of modern youth of the Republic of Sakha (Yakutia)

The subject of the research in this article is the migration sentiments of the modern youth of the Republic of Sakha (Yakutia). For Yakutia, both in Soviet and modern times, the importance of migration has always been enormous. Migration indicators are the most sensitive in relation to the socio-political and economic conditions of the development of the country and the region and require more careful research. The authors consider in detail such aspects of the topic as the socio-demographic characteristics of potential young emigrants from Yakutia, and preferred destinations for migration. Special attention is paid to the identification of the causes of migration that stimulate the active outflow of young people from Yakutia, the factors that shape migration moods among residents of the region. In addition, the article reveals the relationship between the potential migration activity of young people and satisfaction with the standard of living in the region, as well as the experience of traveling abroad. The main research method was a questionnaire survey of residents of Yakutia aged 17 to 35 years, conducted in October 2023. 239 respondents from 9 districts of Yakutia and Yakutsk took part in the survey. The study revealed a high level of migration sentiment among the youth of Yakutia, more than 90% of respondents plan to move to another locality in the future, either to another region or abroad. The share of those wishing to move to another country was 46.6%, to another region of Russia - 52.2%. Emigration sentiments were highest among men aged 17 to 25, single, unemployed and students. The main reasons that encourage young people to emigrate are the desire to improve the quality of life, unfavorable natural and climatic conditions in the north, the desire to travel and a more fulfilling life. Dissatisfaction with the standard of living among young people leads to an increased desire to move to other regions of Russia or abroad.

An Online Hotel Selection Method With Three-Dimensional Analysis of Reviews' Helpfulness

The multi-attribute decision-making method based on online reviews has been widely used in addressing the hotel selection problem. However, due to information overload and the presence of fake reviews, traditional hotel selection methods that rely solely on unverified review analysis can affect the outcome of hotel selections. In this study, a novel three-dimensional helpful review analysis model based multi-attribute decision-making approach for hotel selection is established. Firstly, a new three-dimensional helpful review analysis model that effectively filters out sentiment inconsistency reviews, topic inconsistency reviews, and reviews from invalid sources is proposed. Secondly, this study employs TF-IDF and LDA to extract attributes for hotel selection. We further utilize BERT to extract sentiment level for each attribute. Then, a ranking result for alternative hotels is obtained using a combination compromise solution method (CoCoSo). Finally, we demonstrate its effectiveness and feasibility through a case study of selecting the optimal hotel from TripAdvisor.com.

Detecting Substance Use Disorder Using Social Media Data and the Dark Web: Time- and Knowledge-Aware Study.

Opioid and substance misuse has become a widespread problem in the United States, leading to the "opioid crisis." The relationship between substance misuse and mental health has been extensively studied, with one possible relationship being that substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means. This study aims to analyze social media posts related to substance use and opioids being sold through cryptomarket listings. The study aims to use state-of-the-art deep learning models to generate sentiment and emotion from social media posts to understand users' perceptions of social media. The study also aims to investigate questions such as which synthetic opioids people are optimistic, neutral, or negative about; what kind of drugs induced fear and sorrow; what kind of drugs people love or are thankful about; which drugs people think negatively about; and which opioids cause little to no sentimental reaction. The study used the drug abuse ontology and state-of-the-art deep learning models, including knowledge-aware Bidirectional Encoder Representations From Transformers-based models, to generate sentiment and emotion from social media posts related to substance use and opioids being sold through cryptomarket listings. The study crawled cryptomarket data and extracted posts for fentanyl, fentanyl analogs, and other novel synthetic opioids. The study performed topic analysis associated with the generated sentiments and emotions to understand which topics correlate with people's responses to various drugs. Additionally, the study analyzed time-aware neural models built on these features while considering historical sentiment and emotional activity of posts related to a drug. The study found that the most effective model performed well (statistically significant, with a macro-F1-score of 82.12 and recall of 83.58) in identifying substance use disorder. The study also found that there were varying levels of sentiment and emotion associated with different synthetic opioids, with some drugs eliciting more positive or negative responses than others. The study identified topics that correlated with people's responses to various drugs, such as pain relief, addiction, and withdrawal symptoms. The study provides insight into users' perceptions of synthetic opioids based on sentiment and emotion expressed in social media posts. The study's findings can be used to inform interventions and policies aimed at reducing substance misuse and addressing the opioid crisis. The study demonstrates the potential of deep learning models for analyzing social media data to gain insights into public health issues.

Exploring the Relationship between the Sentiments of Young People and Urban Green Space by Using a Check-In Microblog

Green spaces have a positive impact on the mood of urban residents. However, previous studies have focused primarily on parks or residential areas, neglecting the influence of green spaces in different socioeconomic locations on public sentiment. This oversight fails to acknowledge that most young individuals are exposed to places beyond their homes and parks throughout the day. Using web crawlers, we collected 105,214 Sina Weibo posts from 14,651 geographical check-in points in Hangzhou, Zhejiang Province. We developed a mixed ordered logistic regression model to quantify the relationship between public sentiment (negative/neutral/positive) and the surrounding green space. The findings are as follows: (1) the correlation between GVI and public sentiment is stronger than that between public sentiment and NDVI; (2) among different socioeconomic regions, residential areas are associated with lower levels of public sentiment, while parks are associated with higher levels; and (3) at a scale of 1000 m, an increase of 1% in GVI significantly improves public sentiment regarding transportation hubs, with a regression coefficient of 0.0333. The relationship between green space and public sentiment is intricate and nuanced, and it is influenced by both public activities and spatiotemporal contexts. Urban green space planners should consider additional factors to enhance the effectiveness of green space in improving public sentiment.