Search Results (487)

This research examines the impact of the COVID-19 pandemic on the volatility behavior of Amman Stock Exchange (ASE) returns using ARMA–GARCH-type models for three sub-periods: pre-COVID-19, during COVID-19, and post-COVID-19. The research finds that volatility persistence is significant across all periods, with the pandemic period showing the highest impact of shocks. Bad news has no statistically significant impact on volatility in the pre-COVID-19 period or during the pandemic, while in the post-pandemic period, good news significantly influences volatility. Additionally, there exist notable changes in the autocorrelation and the shock structure of the AR and MA components. Considering these alterations in the asymmetric effects, the AR and MA components suggest significant shifts in market dynamics, investor sentiments, and economic policies in response to pandemic experiences. Full article

This paper takes a political sociological look at the knee-taking in football (or soccer) inspired by the Black Lives Matter campaign. Based upon a study of the new elites, it explores the essence of this performative act and situates it within the ‘obsession’ with racism and anti-racism. Based less on the reality of the problem of racism than upon the emerging values of this new ‘class’, the celebration and promotion of taking the knee is understood as a new type of political etiquette that combines a sense of shame-awareness with a certain contempt for the ‘masses’ who attend football matches. The confusion about whether the support for Black Lives Matter was political or not is discussed with reference to the idea of the changed and to some extent incoherent nature of the modern elites whose values, it is suggested, are more a form of anti-matter than a clear projection of ideas and beliefs. As a result, the quasi-religious nature of the sentiment expressed in modern anti-racism and the action of taking the knee are considered in relation to the ideas of ‘raising awareness’ and of ‘educating yourself’, both of which have an implicitly elitist quality but also lack precision or clarity about either the problem being addressed or any solution to it. Often more therapeutic than overtly political, elite anti-racism is almost by necessity performative, but also comes with a disciplinary dimension for those who refuse to ‘take the knee’ to it. Ultimately, it is suggested that the contestation over the knee-taking gesture reflects a growing cultural divide between the disconnected globalist elites and the more grounded and situated masses who often opposed those who demand their acquiescence towards this performative form of anti-racism. Full article

The Rohingya crisis has been a significant issue for national and international news media, capturing their attention for an extended period and documenting various phases of the crisis. Previous research exploring the tones and portrayal of the Rohingyas in the news lacks comparative and temporal analysis of news sentiments. In this study, we aim to fill this gap by analyzing 8074 news stories on Rohingya issues published in 10 news media outlets from 10 countries between 2009 and 2023. Our computational sentiment analysis reveals that Rohingya-related news sentiments are predominantly negative and fluctuate over the years across different countries, showing little identifiable patterns. An ANOVA suggests significant variation in news sentiments among countries, with some countries exhibiting more similar sentiments than others, thus creating distinguishable groups. Some of our findings contradict previous scholarships, warranting further research and novel frameworks. Additionally, we encourage scrutiny of academic insights to address potential biases against news media’s journalistic integrity. Full article

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop. Full article

Emotion recognition plays an increasingly important role in today’s society and has a high social value. However, current emotion recognition technology faces the problems of insufficient feature extraction and imbalanced samples when processing speech and text information, which limits the performance of existing models. To overcome these challenges, this paper proposes a multi-modal emotion recognition method based on speech and text. The model is divided into two channels. In the first channel, the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) feature set is extracted from OpenSmile, and the original eGeMAPS feature set is merged with the wavelet transformed eGeMAPS feature set. Then, speech features are extracted through a sparse autoencoder. The second channel extracts text features through the BERT-RoBERTa model. Then, deeper text features are extracted through a gated recurrent unit (GRU), and the deeper text features are fused with the text features. Emotions are identified by the attention layer, the dual-layer Bidirectional Long Short-Term Memory (BiLSTM) model, and the loss function, combined with cross-entropy loss and focus loss. Experiments show that, compared with the existing model, the WA and UA of this model are 73.95% and 74.27%, respectively, on the imbalanced IEMOCAP dataset, which is superior to other models. This research result effectively solves the problem of feature insufficiency and sample imbalance in traditional sentiment recognition methods, and provides a new way of thinking for sentiment analysis application. Full article

In recent years, cryptocurrencies have received substantial attention from investors, researchers and the media due to their volatile behaviour and potential for high returns. This interest has led to an expanding body of research aimed at predicting cryptocurrency prices, which are notably influenced by a wide array of technical, sentimental, and legal factors. This paper reviews scholarly content from 2014 to 2024, employing a systematic approach to explore advanced quantitative methods for cryptocurrency price prediction. It encompasses a broad spectrum of predictive models, from early statistical analyses to sophisticated machine and deep learning algorithms. Notably, this review identifies and discusses the integration of emerging technologies such as Transformers and hybrid deep learning models, which offer new avenues for enhancing prediction accuracy and practical applicability in real-world scenarios. By thoroughly investigating various methodologies and parameters influencing cryptocurrency price predictions, including market sentiment, technical indicators, and blockchain features, this review highlights the field’s complexity and rapid evolution. The analysis identifies significant research gaps and under-explored areas, providing a foundational guideline for future studies. These guidelines aim to connect theoretical advancements with practical, profit-driven applications in cryptocurrency trading, ensuring that future research is both innovative and applicable. Full article

Our research evaluates advanced artificial (AI) methodologies to enhance diagnostic accuracy in pulmonary radiography. Utilizing DenseNet121 and ResNet50, we analyzed 108,948 chest X-ray images from 32,717 patients and DenseNet121 achieved an area under the curve (AUC) of 94% in identifying the conditions of pneumothorax and oedema. The model’s performance surpassed that of expert radiologists, though further improvements are necessary for diagnosing complex conditions such as emphysema, effusion, and hernia. Clinical validation integrating Latent Dirichlet Allocation (LDA) and Named Entity Recognition (NER) demonstrated the potential of natural language processing (NLP) in clinical workflows. The NER system achieved a precision of 92% and a recall of 88%. Sentiment analysis using DistilBERT provided a nuanced understanding of clinical notes, which is essential for refining diagnostic decisions. XGBoost and SHapley Additive exPlanations (SHAP) enhanced feature extraction and model interpretability. Local Interpretable Model-agnostic Explanations (LIME) and occlusion sensitivity analysis further enriched transparency, enabling healthcare providers to trust AI predictions. These AI techniques reduced processing times by 60% and annotation errors by 75%, setting a new benchmark for efficiency in thoracic diagnostics. The research explored the transformative potential of AI in medical imaging, advancing traditional diagnostics and accelerating medical evaluations in clinical settings. Full article

No form of economic activity is unaffected by climate change, which has emerged as a new risk factor impacting financial market stability and sustainable development. This study examines the impact of extreme weather on the stock returns of A-share listed companies in China. Utilizing a decade-long dataset, we construct monthly proportions of extreme high-temperature days and extreme humid days using a percentile comparison approach. The findings reveal a significant negative impact of extreme weather on stock returns. Specifically, each standard deviation increase in the monthly proportion of extreme high-temperature days and extreme humid days corresponds to a decrease in annualized returns by 0.09% and 0.15%, respectively. The mediation analysis suggests that extreme weather primarily affects stock returns through its influence on investor sentiment, impacting economic decision making, with minimal direct effects on corporate performance. Additionally, the sensitivity of stock returns to extreme weather varies notably among different types of companies. Larger, more profitable, and less risky firms show lower sensitivity to extreme weather. The impact is observed not only in heat-sensitive industries but also in non-heat-sensitive industries and remains significant even after excluding company announcement days. This study offers new insights and relevant recommendations for businesses and policymakers on sustainable development and financial stability. Full article

Standard machine learning and deep learning architectures have been widely used in the field of sentiment analysis, but their performance is unsatisfactory if the input texts are short (e.g., social media posts). Specifically, the accuracy of standard machine learning methods crucially depends on the richness and completeness of the features used to represent the texts, and in the case of short messages, it is often difficult to obtain high-quality features. Conversely, methods based on deep learning can achieve better expressiveness, but these methods are computationally demanding and often suffer from over-fitting. This paper proposes a new adaptive evolutionary computational integrated learning model (AdaECELM) to overcome the problems encountered by traditional machine learning and deep learning models in sentiment analysis for short texts. AdaECELM consists of three phases: feature selection, sub classifier training, and global integration learning. First, a grid search is used for feature extraction and selection of term frequency-inverse document frequency (TF-IDF). Second, cuckoo search (CS) is introduced to optimize the combined hyperparameters in the sub-classifier support vector machine (SVM). Finally, the training set is divided into different feature subsets for sub-classifier training, and then the trained sub-classifiers are integrated and learned using the AdaBoost integrated soft voting method. Extensive experiments were conducted on six real polar sentiment analysis data sets. The results show that the AdaECELM model outperforms the traditional ML comparison methods according to evaluation metrics such as accuracy, precision, recall, and F1-score in all cases, and we report an improvement in accuracy exceeding 4.5%, the second-best competitor. Full article

Predicting the directions of financial markets has been performed using a variety of approaches, and the large volume of unstructured data generated by traders and other stakeholders on social media microblog platforms provides unique opportunities for analyzing financial markets using additional perspectives. Pretrained large language models (LLMs) have demonstrated very good performance on a variety of sentiment analysis tasks in different domains. However, it is known that sentiment analysis is a very domain-dependent NLP task that requires knowledge of the domain ontology, and this is particularly the case with the financial domain, which uses its own unique vocabulary. Recent developments in NLP and deep learning including LLMs have made it possible to generate actionable financial sentiments using multiple sources including financial news, company fundamentals, technical indicators, as well social media microblogs posted on platforms such as StockTwits and X (formerly Twitter). We developed a financial social media sentiment analyzer (FinSoSent), which is a domain-specific large language model for the financial domain that was pretrained on financial news articles and fine-tuned and tested using several financial social media corpora. We conducted a large number of experiments using different learning rates, epochs, and batch sizes to yield the best performing model. Our model outperforms current state-of-the-art FSA models based on over 860 experiments, demonstrating the efficacy and effectiveness of FinSoSent. We also conducted experiments using ensemble models comprising FinSoSent and the other current state-of-the-art FSA models used in this research, and a slight performance improvement was obtained based on majority voting. Based on the results obtained across all models in these experiments, the significance of this study is that it highlights the fact that, despite the recent advances of LLMs, sentiment analysis even in domain-specific contexts remains a difficult research problem. Full article

Air pollution remains a major public health concern globally, especially in the Western Balkan countries facing severe air quality problems. This study investigates the relationship between air quality, news media sentiment, and public discourse in Macedonia over a ten-year period (2014–2023). We employed sentiment analysis to examine the emotional tone of news coverage related to air pollution, and topic modeling to uncover recurring themes within news articles. Our analysis revealed a distinct seasonal pattern, with negative media sentiments peaking during winter months when PM10 levels were the highest. This finding aligns with the increased reliance on polluting fuels for winter heating. Interestingly, despite a stable number of neutral articles, a rise in positive-sentiment articles suggests a potential decrease in pollution levels or the effectiveness of new government policies. We identified recurring topics like air quality concerns in specific cities, public unease regarding factories, and ongoing scrutiny of government policies. Emerging topics included the impact of the COVID-19 pandemic on air quality, public discourse surrounding heating practices, and growing concerns about waste management. This study contributes to a deeper understanding of the complex interplay between air pollution data, public discourse, and media framing, offering valuable insights for policymakers and media outlets in Macedonia. Full article

Multimodal Sentiment Analysis (MSA) plays a critical role in many applications, including customer service, personal assistants, and video understanding. Currently, the majority of research on MSA is focused on the development of multimodal representations, largely owing to the scarcity of unimodal annotations in MSA benchmark datasets. However, the sole reliance on multimodal representations to train models results in suboptimal performance due to the insufficient learning of each unimodal representation. To this end, we propose Self-HCL, which initially optimizes the unimodal features extracted from a pretrained model through the Unimodal Feature Enhancement Module (UFEM), and then uses these optimized features to jointly train multimodal and unimodal tasks. Furthermore, we employ a Hybrid Contrastive Learning (HCL) strategy to facilitate the learned representation of multimodal data, enhance the representation ability of multimodal fusion through unsupervised contrastive learning, and improve the model’s performance in the absence of unimodal annotations through supervised contrastive learning. Finally, based on the characteristics of unsupervised contrastive learning, we propose a new Unimodal Label Generation Module (ULGM) that can stably generate unimodal labels in a short training period. Extensive experiments on the benchmark datasets CMU-MOSI and CMU-MOSEI demonstrate that our model outperforms state-of-the-art methods. Full article

The advancement of new energy vehicles (NEVs) represents a strategic initiative to combatting climate change, mitigating the energy crisis, and fostering green growth. Using provincial panel data from China between 2017 and 2022, in this study, we applied machine learning techniques for sentiment analysis of textual reviews, used word frequency statistics to explore consumers’ views on the attributes of new energy vehicles, and constructed a consumer sentiment index to study the impact of consumer sentiment on NEV sales. Considering the dependence of NEVs on a charging station, this paper explores the nonlinear impact of the popularity of charging stations on the relationship between consumer sentiment and sales of new energy vehicles. The findings indicate the potential for enhancement in the areas of space, interior design, and comfort of NEVs. Additionally, consumer sentiment was found to facilitate the diffusion of NEVs, with this effect being heterogeneous across different educational backgrounds, income levels, and ages. Furthermore, the availability of per capita public charging stations was shown to significantly reduce range anxiety and encourage consumer purchasing behavior. Full article

The study described in this paper develops a new technique which permits the execution of an open straddle strategy based on the superior volatility forecast for analyzing historical data. We extend the current litearure by measuring the volatility of an underlying asset in the last predefined period and comparing the actual volatility in currency with historical volatility in currency to make predictions of implied volatility. We calculated stock price volatility through an optimal holding period (OHP) and set up bars of volatility in currency. To obtain this, we solved optimization equations to find maximum and minimum movements in the volatility in currency within the defined range. We placed volatility in currency into percentile rankings and designed a straddle trading strategy based on the last OHP’s volatility in currency. The technique allows for an investor (or trader) to open either short or long positions based on calculations for a selected OHP’s volatility in currency. We applied this strategy to 130 stocks which are traded on CBOE. We developed a trading algorithm which can be used by institutional as well as individual investors. The algorithm is set to determine historical volatility in currency and forecast upcoming volatilities in currency through the understanding of the market sentiment. The empirical findings show that the stocks analyzed with the algorithm generate positive returns along a spectrum of changing volatilities of the underlying assets. Full article

Economic and financial narratives inform market sentiment through the emotions that are triggered and the subjectivity that gets evoked. There is an important connection between narrative, sentiment, and human decision making. In this study, natural language processing is used to extract market sentiment from the narratives using FinBERT, a Python library that has been pretrained on a large financial corpus. A news sentiment index is constructed and shown to be a leading indicator of systemic risk. A rolling regression shows how the impact of news sentiment on systemic risk changes over time, with the importance of news sentiment increasing in more recent years. Monitoring systemic risk is an important tool used by central banks to proactively identify and manage emerging risks to the financial system; it is also a key input into the credit loss provision quantification at banks. Credit loss provision is a key focus area for auditors because of the risk of material misstatement, but finding appropriate sources of audit evidence is challenging. The causal relationship between news sentiment and systemic risk suggests that news sentiment could serve as an early warning signal of increasing credit risk and an effective indicator of the state of the economic cycle. The news sentiment index is shown to be useful as audit evidence when benchmarking trends in accounting provisions, thus informing financial disclosures and serving as an exogenous variable in econometric forecast models. Full article