Search results

The discrepancy between the content of an article and its title is a key characteristic of fake news. Current methods for detecting fake news often ignore the significant difference in length between the content and its title. In addition, relying solely on textual discrepancies between the title and content to distinguish between real and fake news has proven ineffective. The purpose of this paper is to develop a new approach called semantic enhancement network with content–title discrepancy (SEN–CTD), which enhances the accuracy of fake news detection.

The SEN–CTD framework is composed of two primary modules: the SEN and the content–title comparison network (CTCN). The SEN is designed to enrich the representation of news titles by integrating external information and position information to capture the context. Meanwhile, the CTCN focuses on assessing the consistency between the content of news articles and their corresponding titles examining both emotional tones and semantic attributes.

The SEN–CTD model performs well on the GossipCop, PolitiFact and RealNews data sets, achieving accuracies of 80.28%, 86.88% and 84.96%, respectively. These results highlight its effectiveness in accurately detecting fake news across different types of content.

The SEN is specifically designed to improve the representation of extremely short texts, enhancing the depth and accuracy of analyses for brief content. The CTCN is tailored to examine the consistency between news titles and their corresponding content, ensuring a thorough comparative evaluation of both emotional and semantic discrepancies.

During drilling in coal mines, sticking of drill rod (referred to as SDR in this work) is a potential threat to underground safety. However, no practical measures to deter SDR have been developed yet. The purpose of this study is to develop an anti-SDR strategy using proportional-integral-derivative (PID) and compliance control (PIDC). The proposed strategy is compatible with the drilling process currently used in underground coal mines using drill rigs. Therefore, this study aims to contribute to the PIDC strategy for solving SDR.

A hydraulic circuit to reduce SDR was built based on a load-independent flow distribution system, a PID controller was designed to control the inlet hydraulic pressure of the rotation motor and a typical compliance control approach was adopted to control the feed force and displacement. Moreover, the weight and optimal combination of the alternative admittance control parameters for the feed cylinder were obtained by adopting the orthogonal experiment approach. Furthermore, a fuzzy admittance control approach was proposed to control the feed displacement. Experiments were conducted to test the effectiveness of the proposed method.

The experimental results indicated that the PIDC strategy was appropriate and effective for controlling the rotation motor and feed cylinder; thus, the proposed method significantly reduces the SDR during drilling operations in underground coal mines.

As the PIDC strategy solves the SDR problem in underground coal mines, it greatly improves the safety of coal mine operation and decreases the power cost. Consequently, it brings the considerable benefits of coal mine production and vast application prospects in other corresponding fields. Actual drilling conditions are difficult to accurately simulate in a laboratory; thus, for future work, drilling experiments can be conducted in actual underground coal mines.

The PIDC-based anti-SDR strategy proposed in this study satisfactorily controls the rotation motor and feed cylinder and facilitates the feed and rotation movements. Furthermore, the tangible novelty of this study results is that it improves the frequency response of the entire drilling system. The drilling process with PIDC decreased the occurrence of SDR by 50%; therefore, the anti-SDR strategy can significantly improve the safety and efficiency of underground coal mining.

The purpose of this study is to investigate the influencing mechanism of consumers' continuous purchase intention toward the subscriber-based knowledge payment platforms (SBKPPs).

This study obtained 226 valid samples through questionnaire surveys and used partial least square structural equation modeling (PLS-SEM) and fuzzy-set qualitative comparative analysis (fsQCA) methods to elucidate the complex causal patterns of consumers' continuous purchase intention toward the SBKPPs.

The findings revealed that perceived utilitarian value, perceived hedonic value and perceived social value directly affected consumers' continuous purchase intention, while content quality and service quality indirectly affected consumers' continuous purchase intention. In addition, this study also demonstrated that all factors must be combined to play a role, and there exist four configurations resulting in consumers' continuous purchase intention toward the SBKPPs.

The results can help researchers and practitioners better understand the causal patterns of consumers' continuous purchase intention toward the SBKPPs.

This study contributes to the knowledge payment literature by investigating consumers' continuous purchase intention toward the SBKPPs. This study also provides practical enlightenment for the SBKPPs' marketing.

When recommending products to consumers, it is important to be able to accurately predict how consumers will rate them. However, existing collaborative filtering models are difficult to achieve a balance between rating prediction accuracy and complexity. Therefore, the purpose of this paper is to propose an accurate and effective model to predict users’ ratings of products for the accurate recommendation of products to users.

First, we introduce an attention mechanism that dynamically assigns weights to user preferences, highlighting key interaction information and enhancing the model’s understanding of user behavior. Second, a fold embedding strategy is employed to segment user interaction data, increasing the information density of each subset while reducing the complexity of the attention mechanism. Finally, a masking strategy is integrated to mitigate overfitting by concealing portions of user-item interactions, thereby improving the model’s generalization ability.

The experimental results demonstrate that the proposed model significantly minimizes prediction error across five real-world datasets. On average, the evaluation metrics root mean square error (RMSE) and mean absolute error (MAE) are reduced by 9.11 and 13.3%, respectively. Additionally, the Friedman test results confirm that these improvements are statistically significant. Consequently, the proposed model more accurately captures the intrinsic correlation between users and products, leading to a substantial reduction in prediction error.

We propose a novel collaborative filtering model to learn the user-item interaction matrix effectively. Additionally, we introduce a fold embedding strategy to reduce the computational resource consumption of the attention mechanism. Finally, we implement a masking strategy to encourage the model to focus on key features and patterns, thereby mitigating overfitting.

The purpose of this paper is to provide a comprehensive review on electronic word-of-mouth (eWOM) credibility. Further, the authors propose a comprehensive and integrated model on eWOM credibility.

The authors conducted a systematic review of the extant literature on marketing, sociology and psychology to identify the factors that affect eWOM credibility. Further, the authors developed themes and identified factors which lead to eWOM credibility.

Four factors were identified, i.e. content, communicator, context and consumer, which affect eWOM credibility. Several variables associated with these four factors were identified, which result in eWOM credibility. Further, the authors developed 22 propositions to explain the causal relationship between these variables and eWOM credibility.

The conceptual model needs empirical validation across various eWOM platforms, i.e. social networking websites, e-commerce websites, etc.

Managers and e-commerce vendors can use these inputs to develop specific design elements and assessment tools which can help consumers to identify credible eWOM messages. Credible eWOM messages, in turn, will increase the “trust” and “loyalty” of the customers on e-commerce vendors.

This paper provides a conclusive takeaway of eWOM credibility literature by integrating multiple perspectives and arguments from the extant literature. This study also presents an integrated model, which provides a theoretical framework for researchers to further examine the interaction effect of various variables, which results in eWOM credibility.

The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-06-2020-0263

The type 120 emergency valve is an essential braking component of railway freight trains, but corresponding diaphragms consisting of natural rubber (NR) and chloroprene rubber (CR) exhibit insufficient aging resistance and low-temperature resistance, respectively. In order to develop type 120 emergency valve rubber diaphragms with long-life and high-performance, low-temperatureresistant CR and NR were processed.

The physical properties of the low-temperature-resistant CR and NR were tested by low-temperature stretching, dynamic mechanical analysis, differential scanning calorimetry and thermogravimetric analysis. Single-valve and single-vehicle tests of type 120 emergency valves were carried out for emergency diaphragms consisting of NR and CR.

The low-temperature-resistant CR and NR exhibited excellent physical properties. The elasticity and low-temperature resistance of NR were superior to those of CR, whereas the mechanical properties of the two rubbers were similar in the temperature range of 0 °C–150 °C. The NR and CR emergency diaphragms met the requirements of the single-valve test. In the low-temperature single-vehicle test, only the low-temperature sensitivity test of the NR emergency diaphragm met the requirements.

The innovation of this study is that it provides valuable data and experience for future development of type 120 valve rubber diaphragms.

Recognizing every worker's working status instead of only describing the existing construction activities in static images or videos as most computer vision-based approaches do; identifying workers and their activities simultaneously; establishing a connection between workers and their behaviors.

Taking a reinforcement processing area as a research case, a new method for recognizing each different worker's activity through the position relationship of objects detected by Faster R-CNN is proposed. Firstly, based on four workers and four kinds of high-frequency activities, a Faster R-CNN model is trained. Then, by inputting the video into the model, with the coordinate of the boxes at each moment, the status of each worker can be judged.

The Faster R-CNN detector shows a satisfying performance with an mAP of 0.9654; with the detected boxes, a connection between the workers and activities is established; Through this connection, the average accuracy of activity recognition reached 0.92; with the proposed method, the labor consumption of each worker can be viewed more intuitively on the visualization graphics.

With this proposed method, the visualization graphics generated will help managers to evaluate the labor consumption of each worker more intuitively. Furthermore, human resources can be allocated more efficiently according to the information obtained. It is especially suitable for some small construction scenarios, in which the recognition model can work for a long time after it is established. This is potentially beneficial for the healthy operation of the entire project, and can also have a positive indirect impact on structural health and safety.

Despite a significant focus on customer evaluation and sentiment analysis, limited attention has been paid to discrete emotional perspective in terms of the emotionality used in text. This paper aims to extend the general-sentiment dictionary in Chinese to a restaurant-domain-specific dictionary, visualize spatiotemporal sentiment trends, identify the main discrete emotions that affect customers’ ratings in a restaurant setting and identify constituents of influential emotions.

A total of 683,610 online restaurant reviews downloaded from Dianping.com were analyzed by a sentiment dictionary optimized by the authors; the main emotions (joy, love, trust, anger, sadness and surprise) that affect online ratings were explored by using multiple linear regression methods. After tracking these sentiment review texts, Latent Dirichlet Allocation (LDA) and LDA models with term frequency-inverse document frequency as weights were used to find the factors that constitute influential emotions.

The results show that it is viable to optimize or expand sentiment dictionary by word similarity. The findings highlight that love and anger have the highest effect on online ratings. The main factors that constitute consumers’ anger (local characteristics, incorrect food portions and unobtrusive location) and love (comfortable dining atmosphere, obvious local characteristics and complete supporting services) are identified. Different from previous studies, negativity bias is not observed, which poses a question of whether it has to do with Chinese culture.

These findings can help managers monitor the true quality of restaurant service in an area on time. Based on the results, restaurant operators can better decide which aspects they should pay more attention to; platforms can operate better and can have more manageable webpage settings; and consumers can easily capture the quality of restaurants to make better purchase decisions.

This study builds upon the existing general sentiment dictionary in Chinese and, to the best of the authors’ knowledge, is the first to provide a restaurant-domain-specific sentiment dictionary and use it for analysis. It also reveals the constituents of two prominent emotions (love and anger) in the case of restaurant reviews.

The performance of corporations in sustainable development is not only a concern of investors, but has also captured ever-increasing attention from consumers. However, the evidence on how these good practices would ultimately benefit brands economically remains insufficient. This study tests the causal effect between corporate Environmental, Social, and Governance (ESG) performance, media coverage, and brand value to reveal the underlying mechanisms of how consumers would react to high ESG performance.

This study uses panel data regression analysis with a sample of Chinese A-share non-financial listed companies from 2010 to 2021. ESG performance, brand value, and media coverage are assessed with Huazheng ESG Rating, the rankings from the China’s 500 Most Valuable Brands' list published by the World Brand Lab, and media index compiled by the Chinese Research Data Services Platform (CNRDS) respectively.

This research confirmed that ESG performance positively impacted brand value in terms of profitability, and that media coverage played a role as a megaphone in this relationship. Large-scale corporates, compared to small ones, benefited more from good ESG ratings due to increased media coverage.

The findings provide evidence of the megaphone effect of media coverage on the relationship between firms’ ESG engagements and brand value in the product market, which has extended the knowledge of media’s monitoring role in the financial market. And this megaphone effect is strengthened by firm size in which larger firms have spotlight effect in draw public attention due to higher expectations in terms of social responsibility.

This study aims to investigate the role of network in affecting private firms’ internationalization decision. Specifically, it investigates the way that business ties, political ties and status influence an internationalization decision.

On the basis of the survey data collected from Chinese private firms, this study distinguishes business ties from political ties and introduces network status. Binary logistic regression is used to test the hypotheses.

Results show that private firms that have business ties are more likely to internationalize, whereas private firms that have political ties are less likely to internationalize. High-status private firms are more likely to internationalize. Political ties negatively moderate the relationship between business ties and internationalization. High-status firms with political ties are more likely to internationalize.

This study provides theoretical and practical contributions. Results complement previous research on social networks in the context of Chinese private firms and have implications for managers who exert effort to internationalize their firms.