Typical investors start off the day by going through the daily news to get an
intuition about the performance of the market. The speculations based on the
tone of the news ultimately shape their responses towards the market. Today,
computers are being trained to compute the news sentiment so that it can be
used as a variable to predict stock market movements and returns. Some
researchers have even developed news-based market indices to forecast stock
market returns. Majority of the research in the field of news sentiment
analysis has focussed on using libraries like Vader, Loughran-McDonald (LM),
Harvard IV and Pattern. However, are the popular approaches for measuring
financial news sentiment really approaching the problem of sentiment analysis
correctly? Our experiments suggest that measuring sentiments using these
libraries, especially for financial news, fails to depict the true picture and
hence may not be very reliable. Therefore, the question remains: What is the
most effective and accurate approach to measure financial news sentiment? Our
paper explores these questions and attempts to answer them through SENTInews: a
one-of-its-kind financial news sentiment analyzer customized to the Indian
context

使用 SENTInews 定制的金融新闻情感分析器，本文探索了衡量金融新闻情感的最有效和准确的方法，认为使用 Vader、LM、Harvard IV 和 Pattern 等常用方法无法准确描绘金融新闻的真实情况，因此不够可靠。

量化金融新闻情感 -- 我们做的是否正确？

On Quantifying Sentiments of Financial News -- Are We Doing the Right  Things?

News can convey bearish or bullish views on financial assets. Institutional
investors need to evaluate automatically the implied news sentiment based on
textual data. Given the huge amount of news articles published each day, most
of which are neutral, we present a systematic news screening method to identify
the ``true'' impactful ones, aiming for more effective development of news
sentiment learning methods. Based on several liquidity-driven variables,
including volatility, turnover, bid-ask spread, and book size, we associate
each 5-min time bin to one of two specific liquidity modes. One represents the
``calm'' state at which the market stays for most of the time and the other,
featured with relatively higher levels of volatility and trading volume,
describes the regime driven by some exogenous events. Then we focus on the
moments where the liquidity mode switches from the former to the latter and
consider the news articles published nearby impactful. We apply naive Bayes on
these filtered samples for news sentiment classification as an illustrative
example. We show that the screened dataset leads to more effective feature
capturing and thus superior performance on short-term asset return prediction
compared to the original dataset.

该研究以资产预测表现为切入点，提出使用流动性驱动变量筛选对资产影响较大的新闻，并运用朴素贝叶斯分类方法，从而提高短期资产回报预测的准确性。