Do stock bulletin board systems (<scp>BBS</scp>) contain useful information? A viewpoint of interaction between <scp>BBS</scp> quality and predicting ability

Xiong, Xiong; Luo, Chunchun; Zhang, Ye; Lin, Sheng Huang

doi:10.1111/acfi.12448

Cited by 7 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first type manually or computationally counts the number of target words and connects them with a pre‐established dictionary; this refers to dictionary‐based methods (Davis et al, 2012; Davis & Tama‐Sweet, 2012). The other category executes statistical models, such as the support vector machine (Frankel et al, 2016; Purda & Skillicorn, 2015), naïve Bayesian (Huang et al, 2014; Li, 2010; Xiong et al, 2019; Zhu et al, 2017), and latent Dirichlet allocation (Brown et al, 2020). These algorithms can identify the document's target words without any human‐made word list, and then statistically test the relationship between these words and other accounting variables through a supervised or unsupervised learning process.…”

Section: Background and Literature Reviewmentioning

confidence: 99%

From natural language to accounting entries using a natural language processing method

Chen

Huang

2023

Accounting & Finance

View full text Add to dashboard Cite

Bookkeeping is crucial in both accounting and auditing. However, a substantial quantity of accounting information initially recorded using unstructured natural language, which restricts the efficiency and accuracy of bookkeeping. In this study, we exploit proprietary transaction data from three firms to demonstrate the capacity of a word embedding approach based on a neural network model (i.e., Word2vec) for processing transaction‐related natural language and automating bookkeeping practice. Our study contributes to accounting practice and literature by demonstrating a practical application of Word2vec to the construction of an automated bookkeeping system.

show abstract

Section: Background and Literature Reviewmentioning

confidence: 99%

From natural language to accounting entries using a natural language processing method

Chen

Huang

2023

Accounting & Finance

View full text Add to dashboard Cite

show abstract

“…These studies urge us to analyze the search volume of Baidu index [1], which is proposed by the Baidu Inc. accounting for the largest market share in China [2]. On the other hand, several researches display their concern to inspect the impact of information extracted from stock message boards on stock activities (Antweiler and Frank, 2004; Tetlock, 2007; Narayan and Bannigidadmath, 2017; Oliveira et al , 2017; Xiong et al , 2019). To be specific, Xiong et al (2019) empirically validate a considerable positive tie between the Internet information amassed from the online stock Bulletin Board Systems and corresponding returns.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, several researches display their concern to inspect the impact of information extracted from stock message boards on stock activities (Antweiler and Frank, 2004; Tetlock, 2007; Narayan and Bannigidadmath, 2017; Oliveira et al , 2017; Xiong et al , 2019). To be specific, Xiong et al (2019) empirically validate a considerable positive tie between the Internet information amassed from the online stock Bulletin Board Systems and corresponding returns. This inspires us to justify whether the information gleaned from East Money Forum, a finance online forum which occupies the largest group of users, could improve the accuracy of volatility forecasting of Chinese stock market.…”

Section: Introductionmentioning

confidence: 99%

Is Baidu index really powerful to predict the Chinese stock market volatility? New evidence from the internet information

Lang

Wang

et al. 2021

CFRI

View full text Add to dashboard Cite

PurposeThis paper verifies whether popular Internet information from Internet forum and search engine exhibit useful content for forecasting the volatility in Chinese stock market.Design/methodology/approachFirst, the authors’ study commences with several HAR-RV-type models, then the study amplifies them respectively with the posting volume and search frequency to construct HAR-IF-type and HAR-BD-type models. Second, from in-sample and out-of-sample analysis, the authors empirically investigate the interpretive ability, forecasting performance (statistic and economic). Third, various robustness checks are utilized to reconfirm the authors’ findings, including alternative forecast window, alternative evaluation method and alternative stock market. Finally, the authors further discuss the forecasting performance in different forecast horizons (h = 5, 10 and 20) and asymmetric effect of information from Internet forum.FindingsFrom in-sample perspective, the authors discover that posting volume exhibits better analytical ability for Chinese stock volatility than search frequency. Out-of-sample results indicate that forecasting models with posting volume could achieve a superior forecasting performance and increased economic value than competing models.Practical implicationsThese findings can help investors and decision-makers obtain higher forecasting accuracy and economic gains.Originality/valueThis study enriches the existing research findings about the volatility forecasting of stock market from two dimensions. First, the authors thoroughly investigate whether the Internet information could enhance the efficiency and accuracy of the volatility forecasting concerning with the Chinese stock market. Second, the authors find a novel evidence that the information from Internet forum is more superior to search frequency in volatility forecasting of stock market. Third, they find that this study not only compares the predictability of the posting volume and search frequency simply, but it also divides the posting volume into “good” and “bad” segments to clarify its asymmetric effect respectively.HighlightsThis study aims to verify whether posting volume and search frequency contain predictive content for estimating the volatility in Chinese stock market.The forecasting model with posting volume can achieve a superior forecasting performance and increases economic value than competing models.The results are robust in alternative forecast window, alternative evaluation method and alternative market index.The posting volume still can help to forecast future volatility for mid- and long-term forecast horizons. Additionally, the role of posting volume in forecasting Chinese stock volatility is asymmetric.

show abstract

“…Third, within the framework of the complex new media environment, our work emphasises the role of the media in the detection of fraud and its impact on the capital market. We therefore enrich the related research about the financial role of the media, about whether internet data contain valid information for investors and about the incentives of an informed trader to publish confidential data (Xiong et al ., 2019).…”

Section: Introductionmentioning

confidence: 99%

Who detects corporate fraud under the thriving of the new media? Evidence from Chinese‐listed firms

Sun

2020

Accounting & Finance

View full text Add to dashboard Cite

We test the effectiveness of corporate fraud-detection mechanisms and the reaction of the capital market to the information released by the various types of detectors. Using corporate fraud data from 2006 to 2015, we find that the media is the most important external market system used to expose corporate fraud to the public. However, in contrast to the low incidents of fraudulent firms being exposed by analysts and short sellers, firms with abnormal short selling are more likely to be revealed to the public. Furthermore, the market reacts significantly negatively to the frauds exposed by the media.

show abstract

Do stock bulletin board systems (BBS) contain useful information? A viewpoint of interaction between BBS quality and predicting ability

Cited by 7 publications

References 53 publications

From natural language to accounting entries using a natural language processing method

From natural language to accounting entries using a natural language processing method

Is Baidu index really powerful to predict the Chinese stock market volatility? New evidence from the internet information

Who detects corporate fraud under the thriving of the new media? Evidence from Chinese‐listed firms

Contact Info

Product

Resources

About