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.

The common methods for clustering time series are the use of specific distance criteria or the use of standard clustering algorithms. Ensemble clustering is one of the common techniques used in data mining to increase the accuracy of clustering. In this study, based on segmentation, selecting the best segments, and using ensemble clustering for selected segments, a multistep approach has been developed for the whole clustering of time series data.

First, this approach divides the time series dataset into equal segments. In the next step, using one or more internal clustering criteria, the best segments are selected, and then the selected segments are combined for final clustering. By using a loop and how to select the best segments for the final clustering (using one criterion or several criteria simultaneously), two algorithms have been developed in different settings. A logarithmic relationship limits the number of segments created in the loop.

According to Rand's external criteria and statistical tests, at first, the best setting of the two developed algorithms has been selected. Then this setting has been compared to different algorithms in the literature on clustering accuracy and execution time. The obtained results indicate more accuracy and less execution time for the proposed approach.

This paper proposed a fast and accurate approach for time series clustering in three main steps. This is the first work that uses a combination of segmentation and ensemble clustering. More accuracy and less execution time are the remarkable achievements of this study.

In the field of heritage science, especially applied to buildings and artefacts made by organic hygroscopic materials, analyzing the microclimate has always been of extreme importance. In particular, in many cases, the knowledge of the outdoor/indoor microclimate may support the decision process in conservation and preservation matters of historic buildings. This knowledge is often gained by implementing long and time-consuming monitoring campaigns that allow collecting atmospheric and climatic data.

Sometimes the collected time series may be corrupted, incomplete and/or subjected to the sensors' errors because of the remoteness of the historic building location, the natural aging of the sensor or the lack of a continuous check of the data downloading process. For this reason, in this work, an innovative approach about reconstructing the indoor microclimate into heritage buildings, just knowing the outdoor one, is proposed. This methodology is based on using machine learning tools known as variational auto encoders (VAEs), that are able to reconstruct time series and/or to fill data gaps.

The proposed approach is implemented using data collected in Ringebu Stave Church, a Norwegian medieval wooden heritage building. Reconstructing a realistic time series, for the vast majority of the year period, of the natural internal climate of the Church has been successfully implemented.

The novelty of this work is discussed in the framework of the existing literature. The work explores the potentials of machine learning tools compared to traditional ones, providing a method that is able to reliably fill missing data in time series.

Online question-and-answer (Q&A) communities serve as important channels for knowledge diffusion. The purpose of this study is to investigate the dynamic development process of online knowledge systems and explore the final or progressive state of system development. By measuring the nonlinear characteristics of knowledge systems from the perspective of complexity science, the authors aim to enrich the perspective and method of the research on the dynamics of knowledge systems, and to deeply understand the behavior rules of knowledge systems.

The authors collected data from the programming-related Q&A site Stack Overflow for a ten-year period (2008–2017) and included 48,373 tags in the analyses. The number of tags is taken as the time series, the correlation dimension and the maximum Lyapunov index are used to examine the chaos of the system and the Volterra series multistep forecast method is used to predict the system state.

There are strange attractors in the system, the whole system is complex but bounded and its evolution is bound to approach a relatively stable range. Empirical analyses indicate that chaos exists in the process of knowledge sharing in this social labeling system, and the period of change over time is about one week.

This study contributes to revealing the evolutionary cycle of knowledge stock in online knowledge systems and further indicates how this dynamic evolution can help in the setting of platform mechanics and resource inputs.

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.

The research on social media-based academic communication has made great progress with the development of the mobile Internet era, and while a large number of research results have emerged, clarifying the topology of the knowledge label network (KLN) in this field and showing the development of its knowledge labels and related concepts is one of the issues that must be faced. This study aims to discuss the aforementioned issue.

From a bibliometric perspective, 5,217 research papers in this field from CNKI from 2011 to 2021 are selected, and the title and abstract of each paper are subjected to subword processing and topic model analysis, and the extended labels are obtained by taking the merged set with the original keywords, so as to construct a conceptually expanded KLN. At the same time, appropriate time window slicing is performed to observe the temporal evolution of the network topology. Specifically, the basic network topological parameters and the complex modal structure are analyzed empirically to explore the evolution pattern and inner mechanism of the KLN in this domain. In addition, the ARIMA time series prediction model is used to further predict and compare the changing trend of network structure among different disciplines, so as to compare the differences among different disciplines.

The results show that the degree sequence distribution of the KLN is power-law distributed during the growth process, and it performs better in the mature stage of network development, and the network shows more stable scale-free characteristics. At the same time, the network has the characteristics of “short path and high clustering” throughout the time series, which is a typical small-world network. The KLN consists of a small number of hub nodes occupying the core position of the network, while a large number of label nodes are distributed at the periphery of the network and formed around these hub nodes, and its knowledge expansion pattern has a certain retrospective nature. More knowledge label nodes expand from the center to the periphery and have a gradual and stable trend. In addition, there are certain differences between different disciplines, and the research direction or topic of library and information science (LIS) is more refined and deeper than that of journalism and media and computer science. The LIS discipline has shown better development momentum in this field.

KLN is constructed by using extended labels and empirically analyzed by using network frontier conceptual motifs, which reflects the innovation of the study to a certain extent. In future research, the influence of larger-scale network motifs on the structural features and evolutionary mechanisms of KLNs will be further explored.

This study investigates the nexus between the returns on oil prices (OP) and unemployment (UR) while taking into account the influences of two of the most representative measures of uncertainty, the Baker et al. (2016) and Caldara and Iacovello (2021) indexes of economic policy uncertainty (EP) and geopolitical risks (GP), in the relationship.

The authors use data on the US, Canada, France, Italy, Germany and Japan from January 2000 to February 2022 and the UK from January 2000 to December 2021. The authors then apply the continuous wavelet transform (CWT), wavelet coherence (WC), partial wavelet coherence (PWC) and multiple wavelet coherence (MWC) to examine the returns within a time and frequency framework.

The CWT tracks the movement and evolution of individual return series with evidence of high variances and heterogenous tendencies across frequencies that also align with critical events such as the GFC and COVID-19 pandemic. The WC reveals the presence of a bidirectional relationship between OP and UR across economies, showing that the two variables affect each other. The authors’ findings establish the predictive influence of oil price on unemployment in line with theory and also show that the variation in UR can impact the economy and alter the dynamics of OP. The authors employ the PWC and MWC to capture the impact of uncertainty indexes in the co-movement of oil price and unemployment in line with the theory of “investment under uncertainty”. Taking into account the common effects of EP and GP, PWC finds that uncertainty measures significantly drive the co-movement of oil prices and unemployment. This result is robust when the authors control for the influence of economic activity (proxied by the GDP) in the co-movement. Furthermore, the MWC reveals the combined intensity, strength and significance of both oil prices and the uncertainty measures in predicting unemployment across countries.

This study investigates the relationship between oil prices, uncertainty measures and unemployment under a time and frequency approach.

1. Wavelet approaches are used to examine the relationship between oil prices and unemployment in the G7.

2. We account for uncertainty measures in the dynamics of oil prices and unemployment.

3. We observe a bidirectional relationship between oil prices and unemployment.

4. Uncertainty measures significantly drive oil prices and unemployment co-movement.

5. Both oil prices and uncertainty measures significantly drive unemployment.

Wavelet approaches are used to examine the relationship between oil prices and unemployment in the G7.

We account for uncertainty measures in the dynamics of oil prices and unemployment.

We observe a bidirectional relationship between oil prices and unemployment.

Uncertainty measures significantly drive oil prices and unemployment co-movement.

Both oil prices and uncertainty measures significantly drive unemployment.

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.

The comparison between economic growth and the character of monetary policy is one of the most frequently studied issues in policymaking. However, the number of studies incorporating a dynamic time warping approach to analyse the similarity of macroeconomic variables is relatively small.

The study aims at assessing the mutual similarity among various variables representing the financial sector (including the monetary policy by the central bank) and the real sector (e.g. economic growth, industrial production, household consumption expenditure), as well as cross-similarity between both sectors.

The analysis is based on the dynamic time warping (DTW) method, which allows for capturing various dimensions of changes of considered variables. This method is almost non-existent in the literature to compare financial and economic time series. The application of this method constitutes the main area of value added of the research. The analysis includes five variables representing the financial sector and five from the real sector. The study covers four countries: Czechia, Hungary, Poland and Romania and the 2010–2022 period (quarterly data).

The results show that variables representing the financial sector, including those reflecting monetary policy, are weakly correlated with each other, whereas the variables representing the real economy have a solid mutual similarity. As regards individual variables, for example, GDP fluctuations show relatively substantial similarity to ROE fluctuations – especially in Czechia and Hungary. In the case of Hungary and Romania, CAR fluctuations are consistent with GDP fluctuations. In the case of Poland and Hungary, there is a relatively strong similarity between the economy's monetisation and economic growth. Comparing the individual countries, two clusters of countries can be identified. One cluster includes Poland and Czechia, while another covers Hungary and Romania.