Language and Domain Specificity: A Chinese Financial Sentiment Dictionary

Abstract

We use Word2vec to develop a financial sentiment dictionary from 3.1 million Chinese-language financial news articles. Our dictionary maps semantically similar words to a subset of human-expert generated financial sentiment words. In validation tests, our dictionary scores the sentiment of articles consistently with human reading of full articles. In return association tests, our dictionary outperforms and subsumes previous Chinese financial sentiment dictionaries, such as direct translations of Loughran and McDonald’s (2011) English-language financial dictionary. We also generate a list of politically-related positive words that is unique to China; we find that this list has a weaker association with returns than does the list of other positive words. We demonstrate that state media uses more politically-related positive and fewer negative words, and exhibits a sentiment bias. This bias renders the state media’s sentiment as less return-informative. Our findings demonstrate that dictionary-based sentiment analysis exhibits strong language and domain specificity.

On the prediction of stock price crash risk using textual sentiment of management statement

“…In the context of China market, Meng et al (2017) apply the vector normalization method to measure the information value of MD&A section and find it is negatively related with stock price crash risk, but it does not discuss the application of textual tone. Du et al (2022) propose a bespoke financial sentiment dictionary to reflect the linguistic features of Chinese Mandarin. Huang et al (2020) provide a systematic review of the application of textual analysis in China's financial market study.…”

The relative importance of overnight sentiment versus trading-hour sentiment in volatility forecasting

“…For example, Tetlock (2007) and Da et al (2015) use the Harvard IV-4 dictionary and the Lasswell Value dictionary to conduct investor sentiment. Du et al (2022), Li et al (2019), and Sun and Zeng (2022) have developed investor sentiment index based on dictionary approach with respect to Chinese stock market. Unfortunately, there is no well-accepted Chinese financial sentiment dictionary.…”

“…Recognizing this weakness, Li et al (2019) manually expand the Chinese translation of the financial dictionary of Loughran and McDonald (2011). Du et al (2022) further develop a Chinese financial sentiment dictionary from Chinese-language news articles. Both works highlight the importance of using a Chinese dictionary when discussing the relationship between the Chinese stock market and investor sentiment.…”

An Inquiry into the Factors Influencing the Role of Marxist Chineseization on the Discourse System of Chinese-Style Modernization

“…From the viewpoint of construction value, the construction of the Chinese modernization discourse system provides discourse assistance for shaping the correct cognition of Chinese modernization, enhancing the value identity of Chinese modernization, dissolving the hegemony of Western modernization discourse, and interpreting the scientific concept of Chinese modernization. Literature [9] designed a financial emotion dictionary through the test in the financial articles. The expressed emotion conforms to the real emotion of real people reading the same article.…”