Purpose

A composite sentiment index (CSI) from quantitative proxy sentiment indicators is likely to be a lag sentiment measure as it reflects only the information absorbed in the market. Information theories and behavioral finance research suggest that market prices may not adjust to all the available information at a point in time. This study hypothesizes that the sentiment from the unincorporated information may provide possible market leads. Thus, this paper aims to discuss a method to identify the un-incorporated qualitative Sentiment from information unadjusted in the market price to test whether sentiment polarity from the information can impact stock returns. Factoring market sentiment extracted from unincorporated information (residual sentiment or sentiment backlog) in CSI is an essential step for developing an integrated sentiment index to explain deviation in asset prices from their intrinsic value. Identifying the unincorporated Sentiment also helps in text analytics to distinguish between current and future market sentiment.

Design/methodology/approach

Initially, this study collects the news from various textual sources and runs the NVivo tool to compute the corpus data’s sentiment polarity. Subsequently, using the predictability horizon technique, this paper mines the unincorporated component of the news’s sentiment polarity. This study regresses three months’ sentiment polarity (the current period and its lags for two months) on the NIFTY50 index of the National Stock Exchange of India. If the three-month lags are significant, it indicates that news sentiment from the three months is unabsorbed and is likely to impact the future NIFTY50 index. The sentiment is also conditionally tested for firm size, volatility and specific industry sector-dependence. This paper discusses the implications of the results.

Findings

Based on information theories and empirical findings, the paper demonstrates that it is possible to identify unincorporated information and extract the sentiment polarity to predict future market direction. The sentiment polarity variables are significant for the current period and two-month lags. The magnitude of the sentiment polarity coefficient has decreased from the current period to lag one and lag two. This study finds that the unabsorbed component or backlog of news consisted of mainly negative market news or unconfirmed news of the previous period, as illustrated in Tables 1 and 2 and Figure 2. The findings on unadjusted news effects vary with firm size, volatility and sectoral indices as depicted in Figures 3, 4, 5 and 6.

Originality/value

The related literature on sentiment index describes top-down/ bottom-up models using quantitative proxy sentiment indicators and natural language processing (NLP)/machine learning approaches to compute the sentiment from qualitative information to explain variance in market returns. NLP approaches use current period sentiment to understand market trends ignoring the unadjusted sentiment carried from the previous period. The underlying assumption here is that the market adjusts to all available information instantly, which is proved false in various empirical studies backed by information theories. The paper discusses a novel approach to identify and extract sentiment from unincorporated information, which is a critical sentiment measure for developing a holistic sentiment index, both in text analytics and in top-down quantitative models. Practitioners may use the methodology in the algorithmic trading models and conduct stock market research.

中文翻译：

---

考虑未调整的资产定价新闻情绪

目的

来自定量代理情绪指标的综合情绪指数 (CSI) 可能是一种滞后情绪衡量指标，因为它仅反映市场吸收的信息。信息理论和行为金融学研究表明，市场价格可能不会在某个时间点根据所有可用信息进行调整。本研究假设来自未合并信息的情绪可能提供可能的市场线索。因此，本文旨在讨论一种从市场价格中未经调整的信息中识别未纳入的定性情绪的方法，以测试信息中的情绪极性是否会影响股票收益。对从 CSI 中未包含的信息（剩余情绪或情绪积压）中提取的市场情绪进行分解是开发综合情绪指数以解释资产价格与其内在价值的偏差的必要步骤。识别未合并的情绪还有助于文本分析区分当前和未来的市场情绪。

设计/方法/方法

最初，这项研究从各种文本来源收集新闻，并运行 NVivo 工具来计算语料库数据的情绪极性。随后，本文利用可预测性视域技术，挖掘了新闻情感极性的未结合成分。本研究对印度国家证券交易所的 NIFTY50 指数三个月的情绪极性（当前时期及其滞后两个月）进行回归。如果三个月滞后显着，则表明三个月的新闻情绪未被吸收，可能会影响未来的 NIFTY50 指数。该情绪还针对公司规模、波动性和特定行业部门的依赖性进行了有条件的测试。本文讨论了结果的含义。

发现

基于信息理论和实证研究结果，本文证明了识别未包含信息并提取情绪极性以预测未来市场方向是可能的。情绪极性变量在当前时期和两个月的滞后中都很显着。情感极性系数的大小从本期下降到滞后一和滞后二。本研究发现，如表 1 和表 2 以及图 2 所示，未吸收部分或积压的新闻主要包括前一时期的负面市场新闻或未经证实的新闻。未调整新闻效应的发现因公司规模、波动性和行业而异。指数如图 3、4、5 和 6 所示。

原创性/价值

关于情绪指数的相关文献描述了自上而下/自下而上的模型，使用定量代理情绪指标和自然语言处理 (NLP)/机器学习方法从定性信息计算情绪以解释市场回报的差异。NLP 方法使用当前时期的情绪来了解市场趋势，而忽略了上一时期未经调整的情绪。这里的基本假设是市场会立即根据所有可用信息进行调整，这在信息理论支持的各种实证研究中被证明是错误的。本文讨论了一种从未合并信息中识别和提取情绪的新方法，这是在文本分析和自上而下的定量模型中开发整体情绪指数的关键情绪度量。