Online recruitment information as an indicator to appraise enterprise performance

Purpose – Fraudulent financial statements and the manipulation of stock prices can seriously affect investors' judgment of company performance, especially in stock markets in emerging economies. Apart from financial reports, which run the risk of being misreported, are there any other information sources that the public can trust when it comes to the truth about a company's performance? The purpose of this paper is to address this issue by assessing the correlation between online recruitment information and company performance and provide investors with a new framework to assist them in making decisions and to identify fraud. Design/methodology/approach – The research extracted the recruitment information of normal and fraudulent companies separately from the internet by employing techniques of natural language processing, opinion mining and competitive intelligence. A statistical tool was then used to study whether there is a difference in the correlation between the recruitment information intensity (RII) and the annually averaged stock price (AASP) of normal and fraudulent firms. Findings – The experiments showed that recruitment information intensity is significantly correlated to company's stock performance for normal firms, which indicates that the company's recruitment activities are consistent with their performance. But for fraudulent companies, the fact that the result is quite the opposite may imply that the RII discloses the truth when managers make misreports. Practical implications – The findings suggest that the intensity of a company's recruitment information is a valuable element for investors in evaluating the firm, and it also can be used as a reliable tool to assist in identifying fraudulent companies. Originality/value – This paper provided a novel way for the public to break information barriers to reach the truth of companies' performance and avoid misleading fraudulent finance statements. It is also a useful application of natural language processing techniques.