Search results

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.

Forecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.

This study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.

The model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R² values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.

This study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Might the impact of the financial stress on exchange markets be asymmetric and exposed to regime changes? Departing from the existing literature, highlighting that the domestic and foreign financial stress in terms of money market have substantial effects on exchange market, this paper aims to investigate the impacts of the bond yield spreads of three emerging countries (Mexico, Russia, and South Korea) on their exchange market pressure indices using monthly observations for the period 2010:01–2019:12. Additionally, the paper analyses the impact of bond yield spread of the US on the exchange market pressure indices of the three mentioned emerging countries. The authors hypothesized whether the negative and positive changes in the bond yield spreads have varying effects on exchange market pressure indices.

To address the research question, we measure the bond yield spread of the selected countries by using the interest rate spread between 10-year and 3-month treasury bills. At the same time, the exchange market pressure index is proxied by the index introduced by Desai et al. (2017). We base the empirical analysis on nonlinear vector autoregression (VAR) models and an asymmetric quantile-based approach.

The results of the impulse response functions indicate that increases/decreases in the bond yield spreads of Mexico, Russia and South Korea raise/lower their exchange market pressure, and the effects of shocks in the bond yield spreads of the US also lead to depreciation/appreciation pressures in the local currencies of the emerging countries. The quantile connectedness analysis, which allows for the role of regimes, reveals that the weights of the domestic and foreign bond yield spread in explaining variations of exchange market pressure indices are higher when exchange market pressure indices are not in a normal regime, indicating the role of extreme development conditions in the exchange market. The quantile regression model underlines that an increase in the domestic bond yield spread leads to a rise in its exchange market pressure index during all exchange market pressure periods in Mexico, and the relevant effects are valid during periods of high exchange market pressure in Russia. Our results also show that Russia differs from Mexico and South Korea in terms of the factors influencing the demand for domestic currency, and we have demonstrated the role of domestic macroeconomic and financial conditions in surpassing the effects of US financial stress. More specifically, the impacts of the domestic and foreign financial stress vary across regimes and are asymmetric.

This study enriches the literature on factors affecting the exchange market pressure of emerging countries. The results have significant economic implications for policymakers, indicating that the exchange market pressure index may trigger a financial crisis and economic recession.

The purpose of this paper is to bridge the gap between the existing theoretical and empirical studies by examining the asymmetric return–volume relationship. Indeed, the authors aim to shed light on the return–volume linkages for French-listed small and medium-sized enterprises (SMEs) compared to blue chips across different market regimes.

This study includes both large capitalizations included in the CAC 40 index and listed SMEs included in the Euronext Growth All Share index. The Markov-switching (MS) approach is applied to understand the asymmetric relationship between trading volume and stock returns. The study investigates also the causal impact between stock returns and trading volume using regime-dependent Granger causality tests.

Asymmetric contemporaneous and lagged relationships between stock returns and trading volume are found for both large capitalizations and listed SMEs. However, the causality investigation reveals some differences between large capitalizations and SMEs. Indeed, causal relationships depend on market conditions and the size of the market.

This paper explains the asymmetric return–volume relationship for both large capitalizations and listed SMEs by incorporating several psychological biases, such as the disposition effect, investor overconfidence and self-attribution bias. Future research needs to deepen the analysis especially for SMEs as most of the literature focuses on large capitalizations.

This empirical study has fundamental implications for portfolio management. The findings provide a deeper understanding of how trading activity impact current returns and vice versa. The authors’ results constitute an important input to build and control trading strategies.

This paper fills the literature gap on the asymmetric return–volume relationship across different regimes. To the best of the authors’ knowledge, the present study is the first empirical attempt to test the asymmetric return–volume relationship for listed SMEs by using an accurate MS framework.

The main objective of our study is to shed light on how perceived enjoyment influences the intricate relationship between value cocreation and consumer satisfaction, with a specific focus on the realms of tourist services.

To achieve the objective outlined in this research, an information survey was carried out on 400 consumers of tourist services who have participated in virtual cocreation processes through digital platforms. As a data analysis technique, the dynamic structural equation modeling (DSEM) analyzes the causal relationships between the elements under study.

Our extensive analysis draws upon the data collected through a survey spanning from 2018 to 2023, encompassing 400 participants who actively engaged in value cocreation processes in both physical and virtual settings. Our investigation considers two competing models to elucidate the role of perceived enjoyment. Our findings, established through DSEM illuminates that perceived enjoyment predominantly functions as a mediator, exerting a more pronounced influence on the connection between value cocreation and consumer satisfaction. Contrary to a moderating role, perceived enjoyment emerges as a significant mediator in our study.

The most significant addition is recognizing virtual value cocreation behaviors in tourist sector activities over time, primarily because it indicates the likelihood of negative repercussions of its usage. Furthermore, it must be capable of designing surroundings according to the characteristics of customers in terms of immersion and technology usage, preventing a rise in stress situations that might result in more negative consequences than planned. Another important insight is that virtual value cocreation initiatives have detrimental long-term implications, particularly in tourism.

The variance between the winning bid and the owner's estimated cost (OEC) is one of the construction management risks in the pre-tendering phase. The study aims to enhance the quality of the owner's estimation for predicting precisely the contract cost at the pre-tendering phase and avoiding future issues that arise through the construction phase.

This paper integrated artificial neural networks (ANN), deep neural networks (DNN) and time series (TS) techniques to estimate the ratio of a low bid to the OEC (R) for different size contracts and three types of contracts (building, electric and mechanic) accurately based on 94 contracts from King Saud University. The ANN and DNN models were evaluated using mean absolute percentage error (MAPE), mean sum square error (MSSE) and root mean sums square error (RMSSE).

The main finding is that the ANN provides high accuracy with MAPE, MSSE and RMSSE a 2.94%, 0.0015 and 0.039, respectively. The DNN's precision was high, with an RMSSE of 0.15 on average.

The owner and consultant are expected to use the study's findings to create more accuracy of the owner's estimate and decrease the difference between the owner's estimate and the lowest submitted offer for better decision-making.

This study fills the knowledge gap by developing an ANN model to handle missing TS data and forecasting the difference between a low bid and an OEC at the pre-tendering phase.

Understandings of house prices and their interrelationships have undoubtedly drawn a great amount of attention from various market participants. This study aims to investigate the monthly newly-built residential house price indices of seventy Chinese cities during a 10-year period spanning January 2011–December 2020 for understandings of issues related to their interdependence and synchronizations.

Analysis here is facilitated through network analysis together with topological and hierarchical characterizations of price comovements.

This study determines eight sectoral groups of cities whose house price indices are directly connected and the price synchronization within each group is higher than that at the national level, although each shows rather idiosyncratic patterns. Degrees of house price comovements are generally lower starting from 2018 at the national level and for the eight sectoral groups. Similarly, this study finds that the synchronization intensity associated with the house price index of each city generally switches to a lower level starting from early 2019.

Results here should be of use to policy design and analysis aiming at housing market evaluations and monitoring.

Economic literature highlights both positive and negative impact of FDI on economic growth. The purpose of this study is to confirm the relationship between various economic factors and FDI equity inflows and find out deviations, if any. This is investigated using standard time-series econometric models. The long and short run relationship is inquired with respect to market size, inflation rate, level of infrastructure, domestic investment and openness to trade. The choice of variables for Indian economy is purely based on empirical observations obtained from scientific literature review.

The study involves application of autoregressive distributive lag (ARDL) model to investigate the relationship. The long run co-integration between FDI and economic growth is tested by Pesaran ARDL model. The stationarity of data is tested by augmented Dickey Fuller test and Phillip–Perron unit root test. Error correction model is applied to study the short run relationship using Johansen’s vector error correction model method besides other tests.

The results show that the domestic investment, inflation rate, level of infrastructure and trade openness influence inward FDI flows. These factors have both long and short-term relationship with FDI inflows. However, market size is insignificant in influencing the foreign investments inflows. There lies an inverse relation between FDI and inflation rate.

To the best of the authors’ knowledge, the study is original. The methodology and interpretation of results are distinct and different from other similar studies.

Increasing overhang of serviced apartments poses a serious concern to the national property market. This study aims to examine the impacts of macroeconomic determinants, namely, gross domestic product (GDP), consumer confidence index (CF), existing stocks (ES), incoming supply (IS) and completed project (CP) on serviced apartment price changes.

To achieve more accurate, quality price changes, a serviced apartment price index (SAPI) was constructed through a self-developed hedonic price index model. This study has collected 1,567 transaction data in Kuala Lumpur, covering 2009Q1–2018Q4 for price index construction and data were analysed using the vector autoregressive model, the vector error correction model and the fully modified ordinary least squares (OLS) (FMOLS).

Results of the regression model show that only GDP, ES and IS were significantly associated with SAPI, with an R² of 0.7, where both ES and IS have inverse relationships with SAPI. More precisely, it is predicted that the price of serviced apartments will be reduced by 0.56% and 0.21% for every 1% increase in ES and IS, respectively.

Therefore, government monitoring of serviced apartments’ future supply is crucial by enforcing land use-planning regulations via stricter development approval of serviced apartments to safeguard and achieve more stable property prices.

By adopting an innovative approach to estimating the response of price change to supply and demand in a situation where there is no price indicator for serviced apartments, the study addresses the knowledge gap, especially in terms of understanding what are the key determinants of, and to what extent they influence, the SAPI.

The aim of this paper is to explore the possibility of using the Define-Measure-Analyze-Improve-Control (DMAIC) cycle, process mining (PM) and multi-criteria decision methods in an integrated way so that these three elements combined result in a methodology called the Agile DMAIC cycle, which brings more agility and reliability in the execution of the Six Sigma process.

The approach taken by the authors in this study was to analyze the studies arising from this union of concepts and to focus on using PM tools where appropriate to accelerate the DMAIC cycle by improving the first two steps, and to test using the AHP as a decision-making process, to bring more excellent reliability in the definition of indicators.

It was indicated that there was a gain with acquiring indicators and process maps generated by PM. And through the AHP, there was a greater accuracy in determining the importance of the indicators.

Through the results and findings of this study, more organizations can understand the potential of integrating Six Sigma and PM. It was just developed for the first two steps of the DMAIC cycle, and it is also a replicable method for any Six Sigma project where data acquisition through mining is possible.

The authors develop a fully applicable and understandable methodology which can be replicated in other settings and expanded in future research.