Search results

Retail investors are prone to be affected by information dissemination in social media with the rapid development of Web 2.0. The purpose of this study is to recognize the factors that may impact users' retweet behavior, namely information dissemination in the online financial community, through machine learning techniques.

This paper crawled data from the Chinese online financial community (Xueqiu.com) and extracted author-related, content-related, situation-related, stock-related and stock market-related features from the dataset. The best information dissemination prediction model based on these features was determined by evaluating five classifiers with various performance metrics, and the predictability of different feature groups was tested.

Five prevalent classifiers were evaluated with various performance metrics and the random forest classifier was proven to be the best retweet prediction model in the authors’ experiments. Moreover, the predictability of author-related, content-related and market-related features was illustrated to be relatively better than that of the other two feature groups. Several particularly important features, such as the author's followers and the rise and fall of the stock index, were recognized in this paper at last.

This study contributes to in-depth research on information dissemination in the financial domain. The findings of this study have important practical implications for government regulators to supervise public opinion in the financial market.

The purpose of this paper is to detect predefined service attributes and their sentiments from online restaurant reviews, and then to measure the effects of customer sentiments toward service attributes on customer satisfaction (CS) and revisit intention (RVI) simultaneously.

This study proposed a supervised framework to model CS and RVI simultaneously from restaurant reviews. Specifically, the authors detected the predefined service dimensions from online reviews based on random forest. Then, the sentiment polarities of the reviews toward each predefined dimension were identified using light-gradient boosting machine (LightGBM). Finally, the effects of attribute-specific sentiments on CS and RVI were evaluated by a bagged neural network-based model. The proposed framework was evaluated by 305,000 restaurant comments collected from DianPing.com, a Yelp-like website in China.

The authors obtained a hierarchal importance order of the investigated service themes (i.e. location, service, environment, price and food). The authors found that food played the most important role in affecting both CS and RVI. The most salient attribute with respect to each service theme was also identified.

Unlike prior work relying on the data collected from surveys, this study is among the first to model the relationship among service attributes, CS and RVI simultaneously from real-world data. The authors established a hierarchal structure of eighteen attributes within five service themes and estimated their effects on both CS and RVI, which will broaden our understanding of customer perception and behavioral intention during service consumption.

The purpose of this paper is to identify the impact factors that might influence audiences' voluntary donation to content creators on the online platforms, and to build an effective prediction model by considering both content and creator-related features.

This study collected the real-world data of content consumption from Xueqiu.com and extracted both content and creator characteristics from the data set. The best donation prediction model based on such features was determined by evaluating four prevalent classifiers with various performance metrics. Furthermore, three feature selection methods were applied to validate the robustness of the constructed model, and then the predictability of different feature groups was examined. Finally, we conducted an interpretive analysis to identify relatively important predictors.

The experimental results show that the random classifier with all extracted features outperformed other built models and achieved excellent performance, indicating the usefulness of these factors in predicting the donations. Moreover, the predictability of content features was demonstrated to be relatively better than that of creator ones. Finally, several particularly important predictors were identified such as the number of modal particles in the article.

This study is among the first to investigate what factors might drive customers' voluntary donation to content contributors on social websites. Different from previous studies focusing on live video streaming, we expand the research vision by examining the donations to user-generated text content, calling for attention to other important topics in the burgeoning industry.

The purpose of this paper is to investigate the mediating effect of online reviewers' affect (ORA) on the relationship between weather and online review ratings (ORR).

The consumers' online review data were collected from the third-party restaurant website, and the weather data were obtained from the weather part of Chinese e-government website. SnowNLP was utilized to analyze sentiment and further extract ORA. Furthermore, the mediating effects of ORA on temperature and ORR, rain and ORR were explored separately using PROCESS 3 Macro Model 4, and the interaction effect of temperature and rain was tested through PROCESS 3 Macro Model 7.

The findings of this work demonstrate that ORA mediates the relationship between temperature and ORR and the relationship between rain and ORR. Besides directly leading to higher ORR, a higher temperature can bring about higher ORR by elevating ORA. On the other hand, little rain and heavy rain have a direct negative influence on ORR, and they can also lead people into a bad mood state, thus leading to lower ORR. Furthermore, temperature moderates the effect of rain on ORA. When the temperature is higher, the differences of ORA are larger between different types of rain than that of lower temperature.

This study appears to be the first to investigate the relationship among weather, ORA and ORR using online data. The results could help managers understand when consumers are more likely to provide negative eWOM under corresponding weather conditions and adopt appropriate strategies to improve ORR.

The purpose of this paper is to propose a methodology to construct a stock market sentiment lexicon by incorporating domain-specific knowledge extracted from diverse Chinese media outlets.

This paper presents a novel method to automatically generate financial lexicons using a unique data set that comprises news articles, analyst reports and social media. Specifically, a novel method based on keyword extraction is used to build a high-quality seed lexicon and an ensemble mechanism is developed to integrate the knowledge derived from distinct language sources. Meanwhile, two different methods, Pointwise Mutual Information and Word2vec, are applied to capture word associations. Finally, an evaluation procedure is performed to validate the effectiveness of the method compared with four traditional lexicons.

The experimental results from the three real-world testing data sets show that the ensemble lexicons can significantly improve sentiment classification performance compared with the four baseline lexicons, suggesting the usefulness of leveraging knowledge derived from diverse media in domain-specific lexicon generation and corresponding sentiment analysis tasks.

This work appears to be the first to construct financial sentiment lexicons from over 2m posts and headlines collected from more than one language source. Furthermore, the authors believe that the data set established in this study is one of the largest corpora used for Chinese stock market lexicon acquisition. This work is valuable to extract collective sentiment from multiple media sources and provide decision-making support for stock market participants.

This paper examines China's historiography on foreign education since 1900, with an emphasis on the period since 1949. The understanding of “foreign education” in China during this period shifted rapidly from the Western-centered approach that had been introduced from Japanese during the late Qing dynasty and the Republic of China to the Soviet-centered approach that followed the founding of New China to a restoration of Western-centered approaches after the “opening” of the late 1970s and 1980s. The paper asks: how has the study of foreign educational history changed over time in the People's Republic of China, how has the broader discipline of history of education changed, and how have successive generations of historians of education conceived of their intellectual and political roles?

Grounded in archival documents and the published works of influential historians of education, this study notes the ways in which political regime change affected the construction and application of academic knowledge.

This study identifies four stages in the Chinese historiography on foreign education: a formative stage (from 1900 until the late 1940s); a difficult post-revolutionary recovery, followed by growth and then suppression (from 1949 until the mid-1970s); a period of achievement combined with an academic crisis (from 1978 until the early 2000s); and finally, a recent transition marked by theoretical innovation and global integration (from the 2000s until the present).

This study finds that a narrow focus on “practical utility” or service to politics and policy has perturbed historians of foreign education in China and stunted their field's development. A look back at early periods in the historiography offers a warning about the potential dangers of extreme ideological/political utilitarianism. These dangers existed not only in the history of foreign education but also in the history of education research more broadly. A close examination of these dangers can help twenty-first-century historians of education in China balance the practical, political and professional dimensions of their research. To grasp the meaning of foreign education, historical research needs to be politically independent.