The research of natural language processing (NLP) technology based on statistical machine learning on the investment decision of port and shipping enterprises

DOI

10.2991/978-94-6463-262-0_40How to use a DOI?

Keywords

transportation economics; NLP; domain sentiment lexicon; LASSO; Fama-MacBeth; annual report tone; financial performance

Abstract

This paper takes China's listed port and shipping companies as the research object, and uses 426 Chinese annual reports from 2001 to 2021 as a text corpus to quantify the emotional tone of the annual report texts of port and shipping companies based on natural language processing (NLP) of statistical machine learning. Study the relationship between the emotional tone index of the annual report text of port and shipping listed companies and the financial performance of the company. The innovations and characteristics of this paper are as follows: Firstly, construct a dictionary of emotional intonation in the field of port and shipping, and use this as a basis to construct an index of emotional intonation in annual reports of listed companies in port and shipping. The second is to establish a two-stage research method to study the relationship between the emotional tone of the annual report text of port and shipping listed companies and the financial performance of the company. In the first stage, the improved LASSO model is used to screen the control variables. In the second stage, a two-step regression based on the Fama-MacBeth model is used to explore the relationship between text tone and financial performance. The study found that the emotional tone index of annual reports constructed based on statistical machine learning NLP technology is significantly negatively correlated with the financial performance of port and shipping companies, which shows that the more positive (negative) the tone of the annual report of listed companies in port and shipping companies, the worse the financial performance of the company (good). The research results provide an analysis tool for the application of NLP technology in the field of port and shipping. It also provides decision support for the management and investment of port and shipping enterprises.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Xu Bin
AU  - Gong Xiaoxing
AU  - Xue Xuebo
AU  - Liu Chao
PY  - 2023
DA  - 2023/10/09
TI  - The research of natural language processing (NLP) technology based on statistical machine learning on the investment decision of port and shipping enterprises
BT  - Proceedings of the 3rd International Conference on Management Science and Software Engineering (ICMSSE 2023)
PB  - Atlantis Press
SP  - 361
EP  - 375
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-262-0_40
DO  - 10.2991/978-94-6463-262-0_40
ID  - Bin2023
ER  -