Search results

The purpose of this research study is to improve sentiment analysis (SA) at the aspect level, which is accomplished through two independent goals of aspect term and opinion extraction and subsequent sentiment classification.

The proposed architecture uses neighborhood and dependency tree-based relations for target opinion extraction, a domain–ontology-based knowledge management system for aspect term extraction, and deep learning techniques for classification.

The authors use different deep learning architectures to test the proposed approach of both review and aspect levels. It is reported that Vanilla recurrent neural network has an accuracy of 83.22%, long short-term memory (LSTM) is 89.87% accurate, Bi-LSTM is 91.57% accurate, gated recurrent unit is 65.57% accurate and convolutional neural network is 82.33% accurate. For the aspect level analysis, ρ_aspect comes out to be 0.712 and Δ²_aspect is 0.384, indicating a marked improvement over previously reported results.

This study suggests a novel method for aspect-based SA that makes use of deep learning and domain ontologies. The use of domain ontologies allows for enhanced aspect identification, and the use of deep learning algorithms enhances the accuracy of the SA task.

This study aims to investigate the evolution of terminology in supply chain management (SCM) and its implications for the field’s strategic orientation. It also aims to understand how SCM terms adapt to interdisciplinary contexts, reflecting shifts in theoretical and practical approaches within the discipline.

This study uses a systematic literature review and analyzes over 3,500 unique SCM-related terms extracted from approximately 33,000 abstracts. By using Descending Hierarchical Classification and factor analysis, the research methodologically identifies key shifts in terminology and discerns underlying patterns.

This study categorizes terminological variations in SCM into three main clusters: product–agent, performance objective orientation and structure. These variations signal not only linguistic changes but also strategic shifts in SCM understanding and practice. Notably, terms such as “green,” “sustainable” and “circular” supply chains have emerged in response to evolving internal and external pressures and trends. In addition, this paper offers a nuanced understanding of these terminological adaptations, proposing a reference framework for navigating SCM’s evolving lexicon and highlighting global usage and geographical and cultural nuances in SCM discourse.

This paper presents a reference framework that complements existing SCM definitions, fostering a shared understanding of SCM variations on a global scale. This framework enhances cultural sensitivity within the field and underscores SCM’s adaptability and flexibility. These insights offer a nuanced view of SCM dynamics, benefiting researchers and practitioners alike. Beyond terminology, this study sheds light on the interplay between language and SCM strategy, providing a valuable perspective for navigating the evolving SCM landscape. The study’s scope is constrained by the analyzed abstracts. Future research could broaden this analysis to encompass more SCM literature or delve deeper into the implications of terminological changes.

This study offers practitioners a reference framework for navigating the evolving lexicon of SCM. This framework aids in understanding the strategic implications of terminological changes, enhancing clarity and context in both academic and practical applications.

By acknowledging global usage and variations, the research underscores the impact of geographical and cultural nuances on SCM discourse. This global perspective enriches the understanding of SCM as a dynamic and culturally sensitive field.

This research is novel in its extensive and systematic exploration of SCM terminology. This study offers a comprehensive analysis of how language evolves in tandem with strategic shifts in the field, providing a unique perspective on the interplay between terminology and strategy in SCM.

This empirical study investigates the potential impact on freedom of expression arising from the accumulation of user-generated content on the web. The purpose of this study is to serve as a valuable reference for countries and regions that have not yet implemented web archiving due to similar concerns.

To achieve the goals, the author conducted a web-based survey experiment using sentiment analysis of book reviews as a representation of general topics. This approach enabled the author to objectively examine whether the expression of content undergoes changes in accordance with social conformity theory.

The study’s findings suggest that, at least for general topics, the observed chilling effect is minimal at best. This provides support for the proposition that it is advisable to proceed to the subsequent phase, where more sensitive subjects can be thoroughly explored in the context of web archiving and its associated chilling effects.

To the best of the author’s knowledge, this study is the first attempt to conduct a survey experiment addressing potential chilling effects resulting from the collection of user-generated content. Notably, the measurement of chilling effects remains contentious and comes with inherent limitations, adding a nuanced perspective to the discourse.

Although the effects of both news sentiment and expectations on price in financial markets have now been extensively demonstrated, the jointness that these predictors can have in their effects on price has not been well-defined. Investigating causal ordering in their effects on price can further our understanding of both direct and indirect effects in their relationship to market price.

We use autoregressive distributed lag (ARDL) methodology to examine the relationship between agent expectations and news sentiment in predicting price in a financial market. The ARDL estimation is supplemented by Grainger causality testing.

In the ARDL models we implement, measures of expectations and news sentiment and their lags were confirmed to be significantly related to market price in separate estimates. Our results further indicate that in models of relationships between these predictors, news sentiment is a significant predictor of agent expectations, but agent expectations are not significant predictors of news sentiment. Granger-causality estimates confirmed the causal inferences from ARDL results.

Taken together, the results extend our understanding of the dynamics of expectations and sentiment as exogenous information sources that relate to price in financial markets. They suggest that the extensively cited predictor of news sentiment can have both a direct effect on market price and an indirect effect on price through agent expectations.

Even traditional financial management firms now commonly track behavioral measures of expectations and market sentiment. More complete understanding of the relationship between these predictors of market price can further their representation in predictive models.

This article extends the frequently reported bivariate relationship of expectations and sentiment to market price to examine jointness in the relationship between these variables in predicting price. Inference from ARDL estimates is supported by Grainger-causality estimates.