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.

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.

A time-varying grey Fourier model (TVGFM(1,1,N)) is proposed for the simulation of variable amplitude seasonal fluctuation time series, as the performance of traditional grey models can't catch the time-varying trend well.

The proposed model couples Fourier series and linear time-varying terms as the grey action, to describe the characteristics of variable amplitude and seasonality. The truncated Fourier order N is preselected from the alternative order set by Nyquist-Shannon sampling theorem and the principle of simplicity, then the optimal Fourier order is determined by hold-out method to improve the robustness of the proposed model. Initial value correction and the multiple transformation are also studied to improve the precision.

The new model has a broader applicability range as a result of the new grey action, attaining higher fitting and forecasting accuracy. The numerical experiment of a generated monthly time series indicates the proposed model can accurately fit the variable amplitude seasonal sequence, in which the mean absolute percentage error (MAPE) is only 0.01%, and the complex simulations based on Monte-Carlo method testify the validity of the proposed model. The results of monthly electricity consumption in China's primary industry, demonstrate the proposed model catches the time-varying trend and has good performances, where MAPE_F and MAPE_T are below 5%. Moreover, the proposed TVGFM(1,1,N) model is superior to the benchmark models, grey polynomial model (GMP(1,1,N)), grey Fourier model (GFM(1,1,N)), seasonal grey model (SGM(1,1)), seasonal ARIMA model seasonal autoregressive integrated moving average model (SARIMA) and support vector regression (SVR).

The parameter estimates and forecasting of the new proposed TVGFM are studied, and the good fitting and forecasting accuracy of time-varying amplitude seasonal fluctuation series are testified by numerical simulations and a case study.

This study aims to explore the use of time series analyses to examine changes in travelers’ preferences in accommodation features by disentangling seasonal, trend and the COVID-19 pandemic’s once-off disruptive effects.

Longitudinal data are retrieved by online traveler reviews (n = 519,200) from the Canary Islands, Spain, over a period of seven years (2015 to 2022). A time series analysis decomposes the seasonal, trend and disruptive effects of six prominent accommodation features (view, terrace, pool, shop, location and room).

Single accommodation features reveal different seasonal patterns. Trend analyses indicate long-term trend effects and short-term disruption effects caused by Covid-19. In contrast, no long-term effect of the pandemic was found.

The findings stress the need to address seasonality at the single accommodation feature level. Beyond targeting specific features at different guest groups, new approaches could allow dynamic price optimization. Real-time insight can be used for the targeted marketing of platform providers and accommodation owners.

A novel application of a time series perspective reveals trends and seasonal changes in travelers’ accommodation feature preferences. The findings help better address travelers’ needs in P2P offerings.

This study aims to analyze government hotline text data and generating forecasts could enable the effective detection of public demands and help government departments explore, mitigate and resolve social problems.

In this study, social problems were determined and analyzed by using the time attributes of government hotline data. Social public events with periodicity were quantitatively analyzed via the Prophet model. The Prophet model is decided after running a comparison study with other widely applied time series models. The validation of modeling and forecast was conducted for social events such as travel and educational services, human resources and public health.

The results show that the Prophet algorithm could generate relatively the best performance. Besides, the four types of social events showed obvious trends with periodicities and holidays and have strong interpretable results.

The research could help government departments pay attention to time dependency and periodicity features of the hotline data and be aware of early warnings of social events following periodicity and holidays, enabling them to rationally allocate resources to handle upcoming social events and problems and better promoting the role of the big data structure of government hotline data sets in urban governance innovations.

Owing to highly volatile and chaotic external events, predicting future movements of cryptocurrencies is a challenging task. This paper advances a granular hybrid predictive modeling framework for predicting the future figures of Bitcoin (BTC), Litecoin (LTC), Ethereum (ETH), Stellar (XLM) and Tether (USDT) during normal and pandemic regimes.

Initially, the major temporal characteristics of the price series are examined. In the second stage, ensemble empirical mode decomposition (EEMD) and maximal overlap discrete wavelet transformation (MODWT) are used to decompose the original time series into two distinct sets of granular subseries. In the third stage, long- and short-term memory network (LSTM) and extreme gradient boosting (XGB) are applied to the decomposed subseries to estimate the initial forecasts. Lastly, sequential quadratic programming (SQP) is used to fetch the forecast by combining the initial forecasts.

Rigorous performance assessment and the outcome of the Diebold-Mariano’s pairwise statistical test demonstrate the efficacy of the suggested predictive framework. The framework yields commendable predictive performance during the COVID-19 pandemic timeline explicitly as well. Future trends of BTC and ETH are found to be relatively easier to predict, while USDT is relatively difficult to predict.

The robustness of the proposed framework can be leveraged for practical trading and managing investment in crypto market. Empirical properties of the temporal dynamics of chosen cryptocurrencies provide deeper insights.

House price fluctuations send vital signals to many parts of the economy, and long-term predictions of house prices are of great interest to governments and property developers. Although predictive models based on economic fundamentals are widely used, the common requirement for such studies is that underlying data are stationary. This paper aims to demonstrate the usefulness of alternative filtering methods for forecasting house prices.

We specifically focus on exponential smoothing with trend adjustment and multiplicative decomposition using median house prices for Sydney from Q3 1994 to Q1 2017. The model performance is evaluated using out-of-sample forecasting techniques and a robustness check against secondary data sources.

Multiplicative decomposition outperforms exponential smoothing at forecasting accuracy. The superior decomposition model suggests that seasonal and cyclical components provide important additional information for predicting house prices. The forecasts for 2017–2028 suggest that prices will slowly increase, going past 2016 levels by 2020 in the apartment market and by 2022/2023 in the detached housing market.

We demonstrate that filtering models are simple (univariate models that only require historical house prices), easy to implement (with no condition of stationarity) and widely used in financial trading, sports betting and other fields where producing accurate forecasts is more important than explaining the drivers of change. The paper puts forward a case for the inclusion of filtering models within the forecasting toolkit as a useful reference point for comparing forecasts from alternative models.

To the best of the authors’ knowledge, this paper undertakes the first systematic comparison of two filtering models for the Sydney housing market.

Paper aims to investigate the interdependencies and spillover effects that the Visegrad (V4 hereafter) Equity Markets hold on each other. The V4 group stands for the political alliance of four Central European countries: Poland, the Czech Republic, Hungary and Slovakia.

The study uses Wavelet coherence, dynamic conditional correlation GARCH (1, 1) and unrestricted vector autoregression (VAR) methodologies. Daily data series (covering the period from January 2, 2006, to February 2, 2023) are analyzed to assess coherence, time-varying conditional correlation and shock transmission among the V4 Equity Markets.

Wavelet analysis reveals that the Slovak equity market does not maintain coherence with three other equity markets. The time-varying conditional correlation documents for the high interdependence during the COVID-19 outbreak of the four indexes. The VAR estimates reveal that shocks in the Warsaw equity market are easily transmitted in Prague and Budapest exchanges but not in Bratislava. The results show that the Slovak equity market tends to be isolated from the influence of other three V4 exchanges. This isolation is attributed to its size, limited volume and adoption of the euro in 2009. The study emphasizes the Slovak financial system’s gravitation toward the Eurozone after euro adoption.

Notably, the findings provide important signals for local and international investors as the results cover four significant international shocks. The global meltdown of 2008/09, the Greek debt crisis of 2010/11, the COVID-19 pandemic and the Russia-Ukraine war.

Identifying the flow regime is a prerequisite for accurately modeling two-phase flow. This paper aims to introduce a comprehensive data-driven workflow for flow regime identification.

A numerical two-phase flow model was validated against experimental data and was used to generate dynamic pressure signals for three different flow regimes. First, four distinct methods were used for feature extraction: discrete wavelet transform (DWT), empirical mode decomposition, power spectral density and the time series analysis method. Kernel Fisher discriminant analysis (KFDA) was used to simultaneously perform dimensionality reduction and machine learning (ML) classification for each set of features. Finally, the Shapley additive explanations (SHAP) method was applied to make the workflow explainable.

The results highlighted that the DWT + KFDA method exhibited the highest testing and training accuracy at 95.2% and 88.8%, respectively. Results also include a virtual flow regime map to facilitate the visualization of features in two dimension. Finally, SHAP analysis showed that minimum and maximum values extracted at the fourth and second signal decomposition levels of DWT are the best flow-distinguishing features.

This workflow can be applied to opaque pipes fitted with pressure sensors to achieve flow assurance and automatic monitoring of two-phase flow occurring in many process industries.

This paper presents a novel flow regime identification method by fusing dynamic pressure measurements with ML techniques. The authors’ novel DWT + KFDA method demonstrates superior performance for flow regime identification with explainability.

Although proactive fault handling plans are widely spread, many unexpected data center outages still occurred. To rescue the jobs from faulty data centers, the authors propose a novel independent job rescheduling strategy for cloud resilience to reschedule the task from the faulty data center to other working-proper cloud data centers, by jointly considering job nature, timeline scenario and overall cloud performance.

A job parsing system and a priority assignment system are developed to identify the eligible time slots for the jobs and prioritize the jobs, respectively. A dynamic job rescheduling algorithm is proposed.

The simulation results show that our proposed approach has better cloud resiliency and load balancing performance than the HEFT series approaches.

This paper contributes to the cloud resilience by developing a novel job prioritizing, task rescheduling and timeline allocation method when facing faults.