Impact of news sentiment and topics on IPO underpricing: US evidence

Abstract

Purpose The goal of the study is to examine the effects of news sentiment and topics dominating in the news field prior to the initial public offering (IPO) on the IPO underpricing. Design/methodology/approach The authors’ approach has several steps. The first is textual analysis. To detect the dominating topics in the news, the authors use Latent Dirichlet allocation. The authors use bidirectional encoder representations from transformers (BERT) pretrained on financial news corpus to evaluate the tonality of articles. The second is evaluation of feature importance. To this end, a linear regression with robust estimators and Classification and Regression Tree and Random Forest are used. The third is data. The text data consists of 345,731 news articles from Thomson Reuters related to the USA in the date range from 1 January 2011 to 31 May 2018. The data contains all the possible topics from the website, excluding anything related to sports. The sample of 386 initial public offerings completed in the USA from 1 January 2011 to 31 May 2018 was collected from Bloomberg Database. Findings The authors found that sentiment of the media regarding the companies going public influences IPO underpricing. Some topics, namely, the climate change and environmental policies and the trade war between the US and China, have influence on IPO underpricing if they appear in the media prior to the IPO day. Originality/value The puzzle of IPO underpricing is studied from the point of Narrative Economics theory for the first time. While most of the works cover only some specific news segment, we use Thomson Reuters news aggregator, which uses such sources The New York Post, CNN, Fox, Atlantic, The Washington Post ? Buzzfeed. To evaluate the sentiment of the articles, a state-of-the-art approach BERT is used. The hypothesis that some common narratives or topics in the public discussion may impose influence on such example of biased behaviour like IPO underpricing has also found confirmation.

ARIMA-BPNN based Stock Price Prediction Model Based on Fusion News Sentiment Analysis

“…The parallel combination model predicts data values through multiple models and compares them with actual values. The error is larger, the weight is smaller [4].…”

“…Therefore, on the basis of traditional analysis methods, the sentiment analysis section is designed, which combines the differential integration moving average autoregressive model and backpropagation feedforward neural network model to obtain a new combination algorithm model for sentiment analysis fusion, thereby improving the accuracy of stock prediction by the network model. At the same time, the neural network model after sentiment analysis is fused, can further verify the direct relationship between stock market changes and emotional tendencies [4]. There are many current studies on stock prediction, and most of them only improve the prediction model or perform sentiment analysis prediction from the perspective of sentiment tendency, and very few studies that combine the two exist.…”

COVID-19: the impact of the pandemic fear on IPO underpricing

“…We consider FLAIR to be a more preferable text processing method comparing to more traditionally used techniques because this library is simpler in terms of its usage on real data (versus, e.g. neural networks transformers like GPT and BERT (Fedorova et al , 2022)) and does not require large data sets. Moreover, in comparison with classical methods, like an extremely popular bag of words, using FLAIR eliminates the problem of subjectivity when considering libraries, their limitedness in terms of size and the problem of text consideration, as it uses neural networks in its base.…”

“…As has already been mentioned, in addition to exogenous factors, it has become quite popular to use variables stemming from behavioural finance. Generally, macro risks, which IPO underpricing are usually depicted by mass media, as shown by Fedorova et al (2022), affect IPO underpricing. If we take a micro approach, one should pay attention to corporate press releases, public reactions of management (Feng et al, 2022), as well as prospectuses (Yan et al, 2019;Zhang et al, 2022).…”

A Textual Analysis of Logograms in Chinese IPO Roadshows: How Agreement between Investors and Management Relates to Pricing and Performance

“…Early empirical explanations of this anomaly have focused on quantifiable market and financial statement data (Beatty and Ritter 1986;Hanley 1993;Brau et al 2014). Fedorova et al (2022) demonstrate the influence of behavioral characteristics of management on IPO pricing. Finally, Brau et al (2016) focused on the pricing of soft information on IPO pricing using a strategic word dictionary.…”