Search results

Repeat customers play an important role in the restaurant sector. Previous studies have confirmed the positive effect of managerial responses on customer relationship management. However, the practice of managerial response strategies toward repeat customers in the restaurant sector remains unclear. This study aims to explore how social influence and the revisit intention of customers affect the responding behavior of restaurant managers.

This study collects information of 251,944 customer reviews and managerial responses from 1,272 restaurants on Yelp (a leading restaurant review website around the world) and builds four econometric models (with restaurant and month fixed effects) to test the hypotheses empirically.

The empirical results show that restaurant managers are less likely to respond to reviews posted by repeat customers (10% lower than that of new customers). This effect is moderated by customer social influence, which entails that repeat customers with great social influence are more likely to receive managerial responses. Moreover, reviews from repeat customers who have had a longer time since their last consumption are also more likely to receive managerial responses.

The results present implications for restaurant managers in business practice regarding managerial response. Managers should take advantage of platform designs and tools (i.e. customer relationship management programs to keep track of repeat customers) to locate repeat customers and avoid the potential negative effects caused by their selected response strategies.

To the best of the authors’ knowledge, this study is among the first attempts to examine empirically how restaurant managers respond to reviews generated by repeat customers in real business practice and reveals what drives such activities from the perspectives of social influence and revisit intention.

This paper aims to extract the comment targets in Chinese online shopping platform.

The authors first collect the comment texts, word segmentation, part-of-speech (POS) tagging and extracted feature words twice. Then they cluster the evaluation sentence and find the association rules between the evaluation words and the evaluation object. At the same time, they establish the association rule table. Finally, the authors can mine the evaluation object of comment sentence according to the evaluation word and the association rule table. At last, they obtain comment data from Taobao and demonstrate that the method proposed in this paper is effective by experiment.

The extracting comment target method the authors proposed in this paper is effective.

First, the study object of extracting implicit features is review clauses, and not considering the context information, which may affect the accuracy of the feature excavation to a certain degree. Second, when extracting feature words, the low-frequency feature words are not considered, but some low-frequency feature words also contain effective information.

Because of the mass online reviews data, reading every comment one by one is impossible. Therefore, it is important that research on handling product comments and present useful or interest comments for clients.

The extracting comment target method the authors proposed in this paper is effective.

As intelligent technology advances, practical applications often involve data with multiple labels. Therefore, multi-label feature selection methods have attracted much attention to extract valuable information. However, current methods tend to lack interpretability when evaluating the relationship between different types of variables without considering the potential causal relationship.

To address the above problems, we propose an ensemble causal feature selection method based on mutual information and group fusion strategy (CMIFS) for multi-label data. First, the causal relationship between labels and features is analyzed by local causal structure learning, respectively, to obtain a causal feature set. Second, we eliminate false positive features from the obtained feature set using mutual information to improve the feature subset reliability. Eventually, we employ a group fusion strategy to fuse the obtained feature subsets from multiple data sub-space to enhance the stability of the results.

Experimental comparisons are performed on six datasets to validate that our proposal can enhance the interpretation and robustness of the model compared with other methods in different metrics. Furthermore, the statistical analyses further validate the effectiveness of our approach.

The present study makes a noteworthy contribution to proposing a causal feature selection approach based on mutual information to obtain an approximate optimal feature subset for multi-label data. Additionally, our proposal adopts the group fusion strategy to guarantee the robustness of the obtained feature subset.

Hate speech is an expression of intense hatred. Twitter has become a popular analytical tool for the prediction and monitoring of abusive behaviors. Hate speech detection with social media data has witnessed special research attention in recent studies, hence, the need to design a generic metadata architecture and efficient feature extraction technique to enhance hate speech detection.

This study proposes a hybrid embeddings enhanced with a topic inference method and an improved cuckoo search neural network for hate speech detection in Twitter data. The proposed method uses a hybrid embeddings technique that includes Term Frequency-Inverse Document Frequency (TF-IDF) for word-level feature extraction and Long Short Term Memory (LSTM) which is a variant of recurrent neural networks architecture for sentence-level feature extraction. The extracted features from the hybrid embeddings then serve as input into the improved cuckoo search neural network for the prediction of a tweet as hate speech, offensive language or neither.

The proposed method showed better results when tested on the collected Twitter datasets compared to other related methods. In order to validate the performances of the proposed method, t-test and post hoc multiple comparisons were used to compare the significance and means of the proposed method with other related methods for hate speech detection. Furthermore, Paired Sample t-Test was also conducted to validate the performances of the proposed method with other related methods.

Finally, the evaluation results showed that the proposed method outperforms other related methods with mean F1-score of 91.3.

The main novelty of this study is the use of an automatic topic spotting measure based on naïve Bayes model to improve features representation.

This study aims to propose a refined dynamic network slacks-based measure (DNSBM) to evaluate the efficiency of China's regional green innovation system which consists of basic research, applied research and commercialization stages and explore the influencing factors of the stage efficiency.

A two-step procedure is employed. The first step proposes an improved DNSBM model with flexible settings of stages' input or output efficiency and uses second order cone programming (SOCP) to solve the non-linear problem. In the second step, least absolute shrinkage and selection operator (LASSO) and Tobit models are used to explore the influencing factors of the stage efficiency. Global Dynamic Malmquist Productivity Index (GDMPI) and Dagum Gini coefficient decomposition method are introduced for further discussion of the productivity change and regional differences.

On average, Chinese provincial green innovation efficiency should be improved by 24.11% to become efficient. The commercialization stage outperforms the stages of basic research and applied research. Comparisons between the proposed model and input-oriented, output-oriented and non-oriented DNSBM models show that the proposed model is more advanced because it allows some stages to have output-oriented model characteristics while the other stages have input-oriented model characteristics. The examination of the influencing factors reveals that the three stages of the green innovation system have quite diverse influencing factors. Further discussion reveals that Chinese green innovation productivity has increased by 39.85%, which is driven mainly by technology progress, and the increasing tendency of regional differences between northern and southern China should be paid attention to.

This study proposes an improved dynamic three-stage slacks-based measure (SBM) model that allows calculating output efficiency in some stages and input efficiency in the other stages with the application of SOCP approach. In order to capture productivity change, this study develops a GDMPI based on the DNSBM model. In practice, the efficiency of regional green innovation in China and the factors that influence each stage are examined.

The work presents a novel implementation of the generalized minimum residual (GMRES) solver in conjunction with the interpolating meshless local Petrov–Galerkin (MLPG) method to solve steady-state heat conduction in 2-D as well as in 3-D domains.

The restarted version of the GMRES solver (with and without preconditioner) is applied to solve an asymmetric system of equations, arising due to the interpolating MLPG formulation. Its performance is compared with the biconjugate gradient stabilized (BiCGSTAB) solver on the basis of computation time and convergence behaviour. Jacobi and successive over-relaxation (SOR) methods are used as the preconditioners in both the solvers.

The results show that the GMRES solver outperforms the BiCGSTAB solver in terms of smoothness of convergence behaviour, while performs slightly better than the BiCGSTAB method in terms of Central processing Unit (CPU) time.

MLPG formulation leads to a non-symmetric system of algebraic equations. Iterative methods such as GMRES and BiCGSTAB methods are required for its solution for large-scale problems. This work presents the use of GMRES solver with the MLPG method for the very first time.

Forecasting demand of emergency supplies under major epidemics plays a vital role in improving rescue efficiency. Few studies have combined intuitionistic fuzzy set with grey-Markov method and applied it to the prediction of emergency supplies demand. Therefore, this article aims to establish a novel method for emergency supplies demand forecasting under major epidemics.

Emergency supplies demand is correlated with the number of infected cases in need of relief services. First, a novel method called the Intuitionistic Fuzzy TPGM(1,1)-Markov Method (IFTPGMM) is proposed, and it is utilized for the purpose of forecasting the number of people. Then, the prediction of demand for emergency supplies is calculated using a method based on the safety inventory theory, according to numbers predicted by IFTPGMM. Finally, to demonstrate the effectiveness of the proposed method, a comparative analysis is conducted between IFTPGMM and four other methods.

The results show that IFTPGMM demonstrates superior predictive performance compared to four other methods. The integration of the grey method and intuitionistic fuzzy set has been shown to effectively handle uncertain information and enhance the accuracy of predictions.

The main contribution of this article is to propose a novel method for emergency supplies demand forecasting under major epidemics. The benefits of utilizing the grey method for handling small sample sizes and intuitionistic fuzzy set for handling uncertain information are considered in this proposed method. This method not only enhances existing grey method but also expands the methodologies used for forecasting demand for emergency supplies.

1. An intuitionistic fuzzy TPGM(1,1)-Markov method (IFTPGMM) is proposed.

2. The safety inventory theory is combined with IFTPGMM to construct a prediction method.

3. Asymptomatic infected cases are taken to forecast the demand for emergency supplies.

An intuitionistic fuzzy TPGM(1,1)-Markov method (IFTPGMM) is proposed.

The safety inventory theory is combined with IFTPGMM to construct a prediction method.

Asymptomatic infected cases are taken to forecast the demand for emergency supplies.

The purpose of this paper is to design a new trajectory error compensation method to improve the trajectory tracking performance and compliance of the knee exoskeleton in human–exoskeleton interaction motion.

A trajectory error compensation method based on admittance-extended Kalman filter (AEKF) error fusion for human–exoskeleton interaction control. The admittance controller is used to calculate the trajectory error adjustment through the feedback human–exoskeleton interaction force, and the actual trajectory error is obtained through the encoder feedback of exoskeleton and the designed trajectory. By using the fusion and prediction characteristics of EKF, the calculated trajectory error adjustment and the actual error are fused to obtain a new trajectory error compensation, which is feedback to the knee exoskeleton controller. This method is designed to be capable of improving the trajectory tracking performance of the knee exoskeleton and enhancing the compliance of knee exoskeleton interaction.

Six volunteers conducted comparative experiments on four different motion frequencies. The experimental results show that this method can effectively improve the trajectory tracking performance and compliance of the knee exoskeleton in human–exoskeleton interaction.

The AEKF method first uses the data fusion idea to fuse the estimated error with measurement errors, obtaining more accurate trajectory error compensation for the knee exoskeleton motion control. This work provides great benefits for the trajectory tracking performance and compliance of lower limb exoskeletons in human–exoskeleton interaction movements.

Because the dynamic characteristics of the stock market are nonlinear, it is unclear whether stock prices can be predicted. This paper aims to explore the predictability of the stock price index from a long-memory perspective. The authors propose hybrid models to predict the next-day closing price index and explore the policy effects behind stock prices. The paper aims to discuss the aforementioned ideas.

The authors found a long memory in the stock price index series using modified R/S and GPH tests, and propose an improved bi-directional gated recurrent units (BiGRU) hybrid network framework to predict the next-day stock price index. The proposed framework integrates (1) A de-noising module—Singular Spectrum Analysis (SSA) algorithm, (2) a predictive module—BiGRU model, and (3) an optimization module—Grid Search Cross-validation (GSCV) algorithm.

Three critical findings are long memory, fit effectiveness and model optimization. There is long memory (predictability) in the stock price index series. The proposed framework yields predictions of optimum fit. Data de-noising and parameter optimization can improve the model fit.

The empirical data are obtained from the financial data of listed companies in the Wind Financial Terminal. The model can accurately predict stock price index series, guide investors to make reasonable investment decisions, and provide a basis for establishing individual industry stock investment strategies.

If the index series in the stock market exhibits long-memory characteristics, the policy implication is that fractal markets, even in the nonlinear case, allow for a corresponding distribution pattern in the value of portfolio assets. The risk of stock price volatility in various sectors has expanded due to the effects of the COVID-19 pandemic and the R-U conflict on the stock market. Predicting future trends by forecasting stock prices is critical for minimizing financial risk. The ability to mitigate the epidemic’s impact and stop losses promptly is relevant to market regulators, companies and other relevant stakeholders.

Although long memory exists, the stock price index series can be predicted. However, price fluctuations are unstable and chaotic, and traditional mathematical and statistical methods cannot provide precise predictions. The network framework proposed in this paper has robust horizontal connections between units, strong memory capability and stronger generalization ability than traditional network structures. The authors demonstrate significant performance improvements of SSA-BiGRU-GSCV over comparison models on Chinese stocks.

Online health communities (OHCs) are platforms that help health consumers to communicate with each other and obtain social support for better healthcare outcomes. However, it is usually difficult for community members to efficiently find appropriate peers for social support exchange due to the tremendous volume of users and their generated content. Most of the existing user recommendation systems fail to effectively utilize the rich social information in social media, which can lead to unsatisfactory recommendation performance. The purpose of this study is to propose a novel user recommendation method for OHCs to fill this research gap.

This study proposed a user recommendation method that utilized the adapted matrix factorization (MF) model. The implicit user behavior networks and the user influence relationship (UIR) network were constructed using the various social information found in OHCs, including user-generated content (UGC), user profiles and user interaction records. An experiment was conducted to evaluate the effectiveness of the proposed approach based on a dataset collected from a famous online health community.

The experimental results demonstrated that the proposed method outperformed all baseline models in user recommendation using the collected dataset. The incorporation of social information from OHCs can significantly improve the performance of the proposed recommender system.

This study can help users build valuable social connections efficiently, enhance communication among community members, and potentially contribute to the sustainable prosperity of OHCs.

This study introduces the construction of the UIR network in OHCs by integrating various social information. The conventional MF model is adapted by integrating the constructed UIR network for user recommendation.