Search results

Aspect-based sentiment analysis (ASA) is a task of sentiment analysis that requires predicting aspect sentiment polarity for a given sentence. Many traditional techniques use graph-based mechanisms, which reduce prediction accuracy and introduce large amounts of noise. The other problem with graph-based mechanisms is that for some context words, the feelings change depending on the aspect, and therefore it is impossible to draw conclusions on their own. ASA is challenging because a given sentence can reveal complicated feelings about multiple aspects.

This research proposed an optimized attention-based DL model known as optimized aspect and self-attention aware long short-term memory for target-based semantic analysis (OAS-LSTM-TSA). The proposed model goes through three phases: preprocessing, aspect extraction and classification. Aspect extraction is done using a double-layered convolutional neural network (DL-CNN). The optimized aspect and self-attention embedded LSTM (OAS-LSTM) is used to classify aspect sentiment into three classes: positive, neutral and negative.

To detect and classify sentiment polarity of the aspect using the optimized aspect and self-attention embedded LSTM (OAS-LSTM) model. The results of the proposed method revealed that it achieves a high accuracy of 95.3 per cent for the restaurant dataset and 96.7 per cent for the laptop dataset.

The novelty of the research work is the addition of two effective attention layers in the network model, loss function reduction and accuracy enhancement, using a recent efficient optimization algorithm. The loss function in OAS-LSTM is minimized using the adaptive pelican optimization algorithm, thus increasing the accuracy rate. The performance of the proposed method is validated on four real-time datasets, Rest14, Lap14, Rest15 and Rest16, for various performance metrics.

The Kaldor–Hicks (KH) criterion has long been the standard for benefit–cost analyses, but it has also been widely criticized as ignoring equity and, arguably, moral sentiments in general. We suggest the use of an aggregate measure (KHM) instead of KH, where M stands for moral sentiments. KHM simply adds to the traditional KH criterion the requirement that all goods for which there is a willingness to pay or accept count as economic goods. This addition, however, runs up against objections to counting moral sentiments in general and non-paternalistic altruism in particular. We show these concerns are unwarranted and suggest that the KHM criterion is superior to KH because it provides better information.

Expectation states theories linking status and behavior enhance our understanding of how social structures organize behavior in a variety of social settings. Efforts to extend behavioral explanations anchored in state organizing processes based on emotions and sentiments have proceeded slowly. This chapter presents a theory of how emotions organize observable power and prestige orders in groups. Emotions are conceptualized as transitory, intense expressions of positive and negative affect communicated from one actor to another by interaction cues. These cues become the basis of long-lasting sentiments conceptualized as liking and disliking for other actors. Sentiments become the foundation for differentiated social structures and hence, performance expectations. This chapter describes how such a process may occur and develops theoretical principles that link emotions, sentiments, and performance expectations.

This paper works at the intersections of affect control theory, expectation states theory, and social influence network theory. First, we introduce social influence network theory into affect control theory. We show how an influence network may emerge from the pattern of interpersonal sentiments in a group and how the fundamental sentiments that are at the core of affect control theory (dealing with the evaluation, potency, and activity of self and others) may be modified by interpersonal influences. Second, we bring affect control theory and social influence network theory to bear on expectation states theory. In a task-oriented group, where persons’ performance expectations may be a major basis of their interpersonal influence, we argue that persons’ fundamental sentiments may mediate effects of status characteristics on group members’ performance expectations. Based on the linkage of fundamental sentiments and interpersonal influence, we develop an account of the formation of influence networks in groups that is applicable to both status homogeneous and status heterogeneous groups of any size, whether or not they are completely connected, and that is not restricted in scope to task-oriented groups.

The authors compare sentiment level with sentiment shock from different angles to determine which measure better captures the relationship between sentiment and stock returns.

This paper examines the relationship between investor sentiment and contemporaneous stock returns. It also proposes a model of systems science to explain the empirical findings.

The authors find that sentiment shock has a higher explanatory power on stock returns than sentiment itself, and sentiment shock beta exhibits a much higher statistical significance than sentiment beta. Compared with sentiment level, sentiment shock has a more robust linkage to the market factors and the sentiment shock is more responsive to stock returns.

This is the first study to compare sentiment level and sentiment shock. It concludes that sentiment shock is a better indicator of the relationship between investor sentiment and contemporary stock returns.

The purpose of the study is to analyse the impact of COVID-19 on the hospitality industry during the rise of worldwide pandemic crises using Twitter analysis. The study is based on 57,794 English-language tweets mined from Twitter from 1 April 2020 to 15 October 2020. Based on thematic and sentiment analysis, the study found that overall sentiments expressed on Twitter were negative. This chapter contributes to existing knowledge about the COVID-19 crisis and broadens the respondents’ understanding of the potential impacts of the crisis on the most vulnerable tourism and hospitality industry. This research emphasises the sustainable revival of the hospitality industry.

Purpose – This chapter examines how sentiment analysis and web-crawling technology can be used to conduct large-scale data analyses of extremist content online.

Methods/approach – The authors describe a customized web-crawler that was developed for the purpose of collecting, classifying, and interpreting extremist content online and on a large scale, followed by an overview of a relatively novel machine learning tool, sentiment analysis, which has sparked the interest of some researchers in the field of terrorism and extremism studies. The authors conclude with a discussion of what they believe is the future applicability of sentiment analysis within the online political violence research domain.

Findings – In order to gain a broader understanding of online extremism, or to improve the means by which researchers and practitioners “search for a needle in a haystack,” the authors recommend that social scientists continue to collaborate with computer scientists, combining sentiment analysis software with other classification tools and research methods, as well as validate sentiment analysis programs and adapt sentiment analysis software to new and evolving radical online spaces.

Originality/value – This chapter provides researchers and practitioners who are faced with new challenges in detecting extremist content online with insights regarding the applicability of a specific set of machine learning techniques and research methods to conduct large-scale data analyses in the field of terrorism and extremism studies.

The purpose of this chapter is to provide a comprehensive analysis of how sentiments may be a part of, or adjacent to, status generalization. We demonstrate why this problem is so difficult to solve definitively, as many resolutions may exist. Sentiments may present the properties of graded status characteristics but may also be disrupted by processes of the self. Sentiments may have status properties enacted within dyadic interactions. However, sentiments may also be status elements during triadic constellations of actors. Finally, we discuss current research that is underway to provide more empirical evidence to offer confirmation or disconfirmation for some of our proposed models.

We provide a synthesis of literatures, including pieces from group processes, neuroscience, psychology, and network scholarship, to address the relation between sentiment and status processes. Accordingly, this is a conceptual chapter.

We attempt to motivate future research by exploring the many complications of examining these issues.

Understanding how social inequalities may emerge during group interaction allows researchers to address their deleterious effects. Positive sentiments (in other words, “liking”) should bring actors closer together to complete tasks successfully. Ironically, when paired with negative sentiments within task groups, inequalities in group opportunities may result. To address these social inequalities, a thorough understanding of how they develop is necessary, so that efficacious interventions can be adopted.

This deep dive into the relation between sentiment and status processes joins the 25-year quest to understand the issues surrounding this relationship.

The primary objective of this research is to provide a precise interpretation of the constructed machine learning model and produce definitive summaries that can evaluate the influence of investor sentiment on the overall sales of non-fungible token (NFT) assets. To achieve this objective, the NFT hype index was constructed as well as several approaches of XAI were employed to interpret Black Box models and assess the magnitude and direction of the impact of the features used.

The research paper involved the construction of a sentiment index termed the NFT hype index, which aims to measure the influence of market actors within the NFT industry. This index was created by analyzing written content posted by 62 high-profile individuals and opinion leaders on the social media platform Twitter. The authors collected posts from the Twitter accounts that were afterward classified by tonality with a help of natural language processing model VADER. Then the machine learning methods and XAI approaches (feature importance, permutation importance and SHAP) were applied to explain the obtained results.

The built index was subjected to rigorous analysis using the gradient boosting regressor model and explainable AI techniques, which confirmed its significant explanatory power. Remarkably, the NFT hype index exhibited a higher degree of predictive accuracy compared to the well-known sentiment indices.

The NFT hype index, constructed from Twitter textual data, functions as an innovative, sentiment-based indicator for investment decision-making in the NFT market. It offers investors unique insights into the market sentiment that can be used alongside conventional financial analysis techniques to enhance risk management, portfolio optimization and overall investment outcomes within the rapidly evolving NFT ecosystem. Thus, the index plays a crucial role in facilitating well-informed, data-driven investment decisions and ensuring a competitive edge in the digital assets market.

The authors developed a novel index of investor interest for NFT assets (NFT hype index) based on text messages posted by market influencers and compared it to conventional sentiment indices in terms of their explanatory power. With the application of explainable AI, it was shown that sentiment indices may perform as significant predictors for NFT sales and that the NFT hype index works best among all sentiment indices considered.

The purpose of this study is to determine which quantitative metrics are most representative of investor sentiment in the US equity markets. Sentiment is the aggregation of consumers', investors', and producers' thoughts and opinions about the future of the financial markets. By analyzing the change in popular economic indicators, financial market statistics, and sentiment reports, we can gain information on investor reactions. Furthermore, we will use machine learning techniques to develop predictive models that will attempt to forecast whether the stock market will go up or down based on the percent change in these indicators.