Amirreza Ghadiridehkordi, Jia Shao, Roshan Boojihawon, Qianxi Wang and Hui Li
This study examines the role of online customer reviews through text mining and sentiment analysis to improve customer satisfaction across various services within the UK banking…
Abstract
Purpose
This study examines the role of online customer reviews through text mining and sentiment analysis to improve customer satisfaction across various services within the UK banking sector. Additionally, the study analyses sentiment trends over a five-year period.
Design/methodology/approach
Using DistilBERT and Support Vector Machine algorithms, customer sentiments were assessed through an analysis of 20,137 Trustpilot reviews of HSBC, Santander, and Tesco Bank from 2018 to 2023. Data pre-processing steps were implemented to ensure data integrity and minimize noise.
Findings
Both positive and negative sentiments provide valuable insights. The results indicate a high prevalence of negative sentiments related to customer service and communication, with HSBC and Santander receiving 90.8% and 89.7% negative feedback, respectively, compared to Tesco Bank’s 66.8%. Key areas for improvement include HSBC’s credit card services and call center efficiency, which experienced increased negative feedback during the COVID-19 pandemic. The findings also demonstrate that DistilBERT excelled in categorizing reviews, while the SVM model, when combined with customer ratings, achieved 96% accuracy in sentiment analysis.
Research limitations/implications
This study focuses on UK bank consumers of HSBC, Santander, and Tesco Bank. A multi-country or cross-cultural study may further enhance our understanding of the approaches and findings.
Practical implications
Online customer reviews become more informative when categorised by service sector. To enhance customer satisfaction, bank managers should pay attention to both positive and negative reviews, and track trends over time.
Originality/value
The uniqueness of this study lies in its exploration of the importance of categorisation in text-mining-based sentiment analysis, its focus on the influence of both positive and negative sentiments, and its emphasis on tracking sentiment trends over time.
Details
Keywords
Hui Shao, Zhi Xiong, Jianxin Xu, Bing Hua and Song Han
The federated filter created by Carlson has been widely used in multi-sensor integrated navigation. Compared with no-reset federated filter, the reset mode has greater…
Abstract
Purpose
The federated filter created by Carlson has been widely used in multi-sensor integrated navigation. Compared with no-reset federated filter, the reset mode has greater sub-filters’ performance, but faults of any subsystem would affect other healthy subsystems via global fusion and the sub-optimality of sub-filters’ estimation has influence on fault detection sensitivity. It’s a challenge to design a robust reset federated filter.
Design/methodology/approach
The time-varying observation noise is designed to reduce proportions of observation information in faulty sub-filters. A new dynamic information distribution algorithm based on optimal residual chi-square detection function is presented to reduce proportions of faulty sub-filters’ estimation in information fusion filter.
Findings
The robust filtering algorithm represents a filtering strategy for reset federated filter. Compared with fault isolation, the navigation result is smoother by using this algorithm. It has significant benefits in avoiding faulty sensors’ contamination and the performance of federated filter is greatly improved.
Research limitations/implications
The approach described in this paper provides a new method to deal with federated reset filter’s faulty problems. This new robust federated filter algorithm possesses a great potential for various applications.
Practical implications
The approach described in this paper can be used in multi-sensor integrated navigation with no fewer than three sensors.
Originality/value
Compared with conventional approach of fault isolation, the proposed algorithm does not destroy the continuity and integrity of the filtering process. It improves the performance of the federated filter by reducing proportions of faulty observation information. It also reduces the influence of sub-optimality on fault detection sensitivity.
Details
Keywords
Hui Shao and Kenzo Nonami
According to UN estimates more than 2,000 people are killed or maimed every month by land‐mines. Although some mechanical solutions to their removal have been proposed, this is…
Abstract
Purpose
According to UN estimates more than 2,000 people are killed or maimed every month by land‐mines. Although some mechanical solutions to their removal have been proposed, this is still heavily dependent on human manipulation. This study seeks to posit a robotic solution to this extremely hazardous operation.
Design/methodology/approach
Examines an active tele‐operated master‐slave robot hand system in which the master and slave hands have completely different structures.
Findings
A secure grasping strategy with a neuro‐fuzzy position control is optional, involving robust position control and accurate force control.
Originality/value
To the best of the authors' knowledge, the configuration and control system of the tele‐operation master‐slave robotic hand is novel in the applied robotics research field.
Details
Keywords
The growing uses of digital technologies have been creating several new business opportunities. Recently, a new concept has emerged in the literature, the “digital…
Abstract
The growing uses of digital technologies have been creating several new business opportunities. Recently, a new concept has emerged in the literature, the “digital entrepreneurship ecosystem” (DEE). However, it has been empirically understudied. Thus, this study aims to analyze the influence of DEE on entrepreneurial activity. The meta-organization theory was used as a perspective of analysis. A quantitative methodology was applied in a sample that includes data from 28 European countries through the generalized method of moments. It was concluded that the DEE pillars, informal and formal institutions, market conditions, physical infrastructure, human capital and talent and networking and support positively influence entrepreneurial activity. It was also found that the variables knowledge, creation and dissemination and finance have a negative impact on entrepreneurial activity. Several theoretical and empirical contributions are also left for the various stakeholders. The present study is original, as no known studies analyze the influence of DEE on entrepreneurial activity in European countries from the perspective of meta-organization theory.
Details
Keywords
A.V. Ivanchenko and A.S. Tonkoshkur
The electromigration degradation model of nonlinear electrical properties of non‐uniform structures with intercrystallite potential barriers is developed. It allows connecting the…
Abstract
The electromigration degradation model of nonlinear electrical properties of non‐uniform structures with intercrystallite potential barriers is developed. It allows connecting the increasing of near surfaces concentration of volume donors by their migration in electrical field at heating up structures by means of electrical current in the process of degradation. It results in experimentally observed deterioration varistoral properties, deterioration and asymmetrical deformation of currentvoltage characteristics during their exploitation.
Details
Keywords
Rayenda Khresna Brahmana and Maria Kontesa
This paper examines the impact of sharia-compliant debt financing on stock price crash risk. Unlike those previous studies that took Sukuk or sharia-compliant firms, this study…
Abstract
Purpose
This paper examines the impact of sharia-compliant debt financing on stock price crash risk. Unlike those previous studies that took Sukuk or sharia-compliant firms, this study tests the impact of the proportion reported sharia-compliant debt financing in the balance sheet on the risk of price crash of a firm.
Design/methodology/approach
Using the data from 2,752 firm-year observations of 344 Malaysian non-financial listed companies from 2012 to 2019, this article used a robust panel data estimation technique for statistical inferences. This study also employs panel GMM and quantile least squares as the robustness check.
Findings
This study established a negative relationship between sharia-compliant debt financing and stock price crash risk. The robustness checks with different estimation techniques confirm the results. It implies that firms with a more significant proportion of Sharia-compliant financing tend to have lower future stock price crash risk.
Practical implications
Consistent with the Islamic finance literature, the present study contributes to the existing literature on Islamic capital markets from the perspective of stock price crash risk because it is vital for risk management and investment decision-making as a measure of tail risk for stocks. The findings of this research will assist investors in developing portfolio strategies that incorporate firms with higher levels of sharia-compliant debt financing in their balance sheets. Additionally, the results of this study suggest that policymakers and regulatory bodies should consider revising their monitoring approaches for publicly listed firms.
Originality/value
This study is interesting and unique, as it is a pioneer in testing the impact of sharia-compliant debt financing on reducing stock price crash risk.
Details
Keywords
Hang Ngoc My Le, Brendan Thomas O’Connell and Maryam Safari
Drawing from Upper-Echelons Theory (UET), this paper aims to examine whether an increasing number of board members studying and working overseas, especially in Anglo countries…
Abstract
Purpose
Drawing from Upper-Echelons Theory (UET), this paper aims to examine whether an increasing number of board members studying and working overseas, especially in Anglo countries, provides some impetus for increased corporate environmental disclosures (CED) in Vietnam.
Design/methodology/approach
This study used quantitative data collection and analysis. The data collection involved a content analysis of annual, sustainability and integrated reports to capture the quality and quantity of CED. The authors subsequently developed ordered probit models to quantitatively test the hypotheses.
Findings
The authors find that board members studying in Anglo countries positively impact firms’ levels of CED in emerging economies. However, overseas work experience is found to be an insignificant explanatory variable. Further, the findings suggest that, in Vietnam, Chairs appear to be more influential than chief executive officers in affecting CED levels.
Practical implications
Despite the positive influence of overseas study, the authors find overall levels of CED in Vietnam remain relatively low. This suggests the necessity of dialogue about potential reform in CED policies, which could involve the introduction of mandatory reporting requirements. In addition, to enhance sustainability disclosures, shareholders should appoint board members who possess international qualifications.
Originality/value
This study adds to the literature exploring the impacts of Anglo cultural traits of board members on CED levels, within an economy transitioning from a communist ideology to a market-oriented system context. The connection between international study and cultural norms, beliefs and traditions in these countries and their positive influence on directors’ values and attitudes towards CED have not yet been studied. The study also extends UET by examining the potential positive influence of different national contexts on board members’ education levels.
Details
Keywords
Yuanyuan Wu, Eric W.T. Ngai, Pengkun Wu and Chong Wu
The extensive distribution of fake news on the internet (FNI) has significantly affected many lives. Although numerous studies have recently been conducted on this topic, few have…
Abstract
Purpose
The extensive distribution of fake news on the internet (FNI) has significantly affected many lives. Although numerous studies have recently been conducted on this topic, few have helped us to systematically understand the antecedents and consequences of FNI. This study contributes to the understanding of FNI and guides future research.
Design/methodology/approach
Drawing on the input–process–output framework, this study reviews 202 relevant articles to examine the extent to which the antecedents and consequences of FNI have been investigated. It proposes a conceptual framework and poses future research questions.
Findings
First, it examines the “what”, “why”, “who”, “when”, “where” and “how” of creating FNI. Second, it analyses the spread features of FNI and the factors that affect the spread of FNI. Third, it investigates the consequences of FNI in the political, social, scientific, health, business, media and journalism fields.
Originality/value
The extant reviews on FNI mainly focus on the interventions or detection of FNI, and a few analyse the antecedents and consequences of FNI in specific fields. This study helps readers to synthetically understand the antecedents and consequences of FNI in all fields. This study is among the first to summarise the conceptual framework for FNI research, including the basic relevant theoretical foundations, research methodologies and public datasets.
Details
Keywords
Xiao Meng, Chengjun Dai, Yifei Zhao and Yuan Zhou
This study aims to investigate the mechanism of the misinformation spread based on the elaboration likelihood model and the effects of four factors – emotion, topic, authority and…
Abstract
Purpose
This study aims to investigate the mechanism of the misinformation spread based on the elaboration likelihood model and the effects of four factors – emotion, topic, authority and richness – on the depth, breadth and structural virality of misinformation spread.
Design/methodology/approach
The authors collected 2,514 misinformation microblogs and 142,006 reposts from Weibo, used deep learning methods to identify the emotions and topics of misinformation and extracted the structural characteristics of the spreading network using the network analysis method.
Findings
Results show that misinformation has a smaller spread size and breadth than true news but has a similar spread depth and structural virality. The differential influence of emotions on the structural characteristics of misinformation propagation was found: sadness can promote the breadth of misinformation spread, anger can promote depth and disgust can promote depth and structural virality. In addition, the international topic, the number of followers, images and videos can significantly and positively influence the misinformation's spread size, depth, breadth and structural virality.
Originality/value
The influencing factors of the structural characteristics of misinformation propagation are clarified, which is helpful for the detection and management of misinformation.
Details
Keywords
Elena Cerdá-Mansilla, Natalia Rubio and Sara Campo
This study aims to analyze a backchannel account on news of the coronavirus at the beginning of the pandemic, with information not disseminated in official media due to the social…
Abstract
Purpose
This study aims to analyze a backchannel account on news of the coronavirus at the beginning of the pandemic, with information not disseminated in official media due to the social alarm it might cause and the negative image of government management. Specifically, it examines acceptance and dissemination of this type of content in a period of lack of information, while reflecting on what would constitute proper management of this type of channel.
Design/methodology/approach
First, based on a literature review, this study classifies possible explanatory variables of online content dissemination into content richness and psychological content. Second, this study performs sentiment analysis of the Twitter backchannel account @COVID_19NEWS and use Qualitative Comparative Analysis to find causal configurations of variables that obtained a high rate of retweets.
Findings
The results reveal predominance of one combination of three factors in backchannel information diffusion: emotional, identifying and video content. Other interesting combinations of factors were shown to be attractive enough to contribute to success of the tweets.
Practical implications
Knowledge of the main configurations that attract information dissemination in backchannel accounts is useful for public management of a health crisis such as the Covid-19 outbreak. Rather than suppressing these channels, the authors discuss different solutions.
Originality/value
This study advances scholarship on backchannel communications in emergency situations, providing insights to understand and manage such channels.
Propósito
Este estudio analiza una cuenta extraoficial sobre noticias del coronavirus al inicio de la pandemia, con información no difundida en los medios oficiales por su posible repercusión en la alarma social y la imagen negativa de la gestión gubernamental. Concretamente examina la aceptación y difusión de este contenido en un periodo de desinformación, así como reflexiona sobre la gestión de este tipo de canales.
Diseño/metodología/enfoque
En primer lugar, en base a la revisión de la literatura, clasificamos las variables explicativas según la riqueza de contenido y el contenido psicológico. En segundo lugar, sobre la cuenta extraoficial de @COVID_19NEWS en Twitter, realizamos análisis de sentimiento y utilizamos Análisis Comparativo Cualitativo (QCA) para encontrar configuraciones causales de variables que obtuvieron una alta tasa de retweets.
Hallazgos
Los resultados revelan la importancia de una combinación de tres factores en la difusión de información del canal secundario: contenido emocional, identificativo y video. Otras combinaciones de factores también contribuyeron al éxito del tweet.
Implicaciones prácticas
Estas configuraciones podrían ser útiles para la gestión pública ante una crisis sanitaria como la Covid-19, prestando atención a los factores cuya configuración atrae la difusión de información en las RRSS. En lugar de suprimir estos canales, se presentan soluciones para garantizar una colaboración eficaz.
Originalidad/valor
Este estudio realiza una contribución académica a las comunicaciones extraoficiales en situaciones de emergencia, proporcionando información para comprender y gestionar este tipo de canales.
Palabras claves
Covid-19, Coronavirus, Canal extraoficial, Twitter, Análisis cualitativo comparado
Tipo de papel
Trabajo de investigación
目的
在新冠疫情初期, 由于可能引起社会恐慌和政府管理部门的负面形象, 官方媒体缺少相关的新闻报道。本文研究了在这种官方信息匮乏的危机时期, 非正式渠道(backchannel)对于新冠病毒内容的接受和传播情况, 本文同时反思了如何对这类非正式渠道进行正确的管理。
研究设计
基于文献综述, 我们先将在线内容传播的可能解释变量分为内容丰富度和心理内容这两个方面。其次, 我们对推特上的非正式渠道账户@COVID_19NEWS发布的内容进行情感分析, 并使用定性比较分析法来寻找内容获得高转发率的原因。
研究结果
结果显示, 对于非正式渠道信息的成功传播, 情绪化、具有辩认度和包含视频内容这三个要素的组合占主导地位。此外, 其他要素的组合也有来助于推文的成功传播和扩散。
实践意义
了解非正式渠道吸引信息传播的主要原因, 将有利于应对健康危机(例如Covid-19爆发)和进行公共管理。文本讨论了不同的解决方案, 而不是简单地压制这些非正式渠道。
原创性/价值
这项研究推进了危机背景下非正式渠道传播的学术研究, 为理解和管理这类非正式渠道提供了见解。
关键词 - Covid-19, 新冠病毒, 非正式渠道, 推特, 定性比较分析