Sentiment Tools Research Articles

Bridging sentiment and finance: An exploration of BOD statements and bank ratios in Jordan

Purpose: This study explores the intricate interplay between sentiment extracted from Board of Directors (BOD) statements and the traditional financial metrics of banks. It investigates the relationship between a bank’s financial performance, measured by various financial ratios, and the sentiment expressed in BOD statements.Design/methodology/approach: Drawing from a dataset encompassing BOD statements from 15 Jordanian banks spanning 2017 to 2021, sentiment analysis techniques are employed to derive sentiment scores. These scores are then juxtaposed with principal components distilled from financial metrics to examine their predictive relationship.Findings: Preliminary findings reveal significant non-linear patterns between Hu and Liu’s (2004) sentimental analysis (Lui_sen), the Data Science Lab’s (n.d.) multilingual sentiment tool (multi_sen), and the principal components. A subsequent random-effects panel regression further elucidates these relationships, highlighting the significant influence of specific principal components on sentiment scores. This study provides a compelling case for integrating sentiment analysis with traditional financial indicators, offering a more comprehensive toolkit for evaluating bank performance.Research limitations/implications: Future research should explore broader datasets across multiple sectors, to validate the generalisability of the findings beyond the banking sector in Jordan.Practical implications: This research holds implications for investors, analysts, and stakeholders by combining sentiment analysis with traditional financial metrics. It offers deeper insights into the health of banks and the intentions of management. This integrated approach allows stakeholders to make informed decisions and mitigate risks based on a more comprehensive view of banks' financial situations. Additionally, the possibility of real-time sentiment analysis enables the dynamic monitoring of banking institutions' financial health as updated data becomes available.Social implications: The study’s results are valuable to users of financial information, aiding the Association of Banks and the Central Bank of Jordan in formulating policies for the banking sector. Auditors, consultants, and regulatory bodies in Jordan can also benefit from these insights.Originality/value: This is the first study exploring the relationship between sentiment extracted from BOD statements and traditional financial metrics in Jordan. It provides novel evidence of this relationship, contributing to the literature on the integration of textual data analysis and financial performance.

Precision forecasting in perilous times: stock market predictions leveraging google trends and momentum indicators during COVID-19

PurposeThis study explores the complex impact of COVID-19 on India's financial sector, moving beyond simplistic public health vs. economy views. We assess market vulnerabilities and analyze how public sentiment, measured through Google Trends, can predict stock market fluctuations. We propose a novel framework using Google Trends for financial sentiment analysis, aiming to improve understanding and preparedness for future crises.Design/methodology/approachHybrid approach leverages Google Trends as sentiment tool, market data, and momentum indicators like Rate of Change, Average Directional Index and Stochastic Oscillator, to deliver accurate, market insights for informed investment decisions during pandemic.FindingsOur study reveals that the pandemic significantly impacted the Indian financial sector, highlighting its vulnerabilities. Capitalizing on this insight, we built a ground-breaking predictive model with an impressive 98.95% maximum accuracy in forecasting stock market values during such events.Originality/valueTo the best of authors knowledge this model's originality lies in its focus on short-term impact, novel data fusion and methodology, and high accuracy.• Focus on short-term impact: Our model uniquely identifies and quantifies the fleeting effects of COVID-19 on market behavior.• Novel data fusion and framework: A novel framework of sentiment analysis was introduced in the form of Trend Popularity Index. Combining trend popularity index with momentum offers a comprehensive and dynamic approach to predicting market movements during volatile periods.• High predictive accuracy: Achieving the prediction accuracy (98.93%) sets this model apart from existing solutions, making it a valuable tool for informed decision-making.

Beyond sentiment: an algorithmic strategy for identifying evaluations within large text corpora

ABSTRACT In this paper, we propose a new strategy for classifying evaluations in large text corpora, using supervised machine learning (SML). Departing from a conceptual and methodological critique of the use of sentiment measures to recognize object-specific evaluations, we argue that a key challenge consists in determining whether a semantic relationship exists between evaluative expressions and evaluated objects. Regarding sentiment terms as merely potentially evaluative expressions, we thus use a SML classifier to decide whether recognized terms have an evaluative function in relation to the evaluated object. We train and test our classifier on a corpus of 10,004 segments of election coverage from 16 major U.S. news outlets and Tweets by 10 prominent U.S. politicians and journalists. Specifically, we focus on evaluations of political predictions about the outcomes and implications of the 2016 and 2020 U.S. presidential elections. We show that our classifier consistently outperforms both off-the-shelf sentiment tools and a pre-trained transformer-based sentiment classifier. Critically, our classifier correctly discards numerous non-evaluative uses of common sentiment terms, whose inclusion in conventional analyses generates large amounts of false positives. We discuss contributions of our approach to the measurement of object-specific evaluations and highlight challenges for future research.

Negativity and Positivity in the ICU: Exploratory Development of Automated Sentiment Capture in the Electronic Health Record.

To develop proof-of-concept algorithms using alternative approaches to capture provider sentiment in ICU notes. Retrospective observational cohort study. The Multiparameter Intelligent Monitoring of Intensive Care III (MIMIC-III) and the University of California, San Francisco (UCSF) deidentified notes databases. Adult (≥18 yr old) patients admitted to the ICU. We developed two sentiment models: 1) a keywords-based approach using a consensus-based clinical sentiment lexicon comprised of 72 positive and 103 negative phrases, including negations and 2) a Decoding-enhanced Bidirectional Encoder Representations from Transformers with disentangled attention-v3-based deep learning model (keywords-independent) trained on clinical sentiment labels. We applied the models to 198,944 notes across 52,997 ICU admissions in the MIMIC-III database. Analyses were replicated on an external sample of patients admitted to a UCSF ICU from 2018 to 2019. We also labeled sentiment in 1,493 note fragments and compared the predictive accuracy of our tools to three popular sentiment classifiers. Clinical sentiment terms were found in 99% of patient visits across 88% of notes. Our two sentiment tools were substantially more predictive (Spearman correlations of 0.62-0.84, p values < 0.00001) of labeled sentiment compared with general language algorithms (0.28-0.46). Our exploratory healthcare-specific sentiment models can more accurately detect positivity and negativity in clinical notes compared with general sentiment tools not designed for clinical usage.

How has airport service quality changed in the context of COVID-19: A data-driven crowdsourcing approach based on sentiment analysis

Airport service quality (ASQ) is a competitive advantage for airport management in today's airport market. Since the COVID-19 health crisis has unprecedentedly influenced airport regulations and operations, effective measurement of ASQ has become crucial for airport administrations. Surveying travelers' attitudes is useful for ASQ assessment but collecting responses could be time-consuming and costly. Therefore, this paper adopts a data-driven crowdsourcing approach to study ASQ during the COVID-19 pandemic by investigating Google Maps reviews from the 98 busiest U.S. airports. To do so, this study develops a topical ontology of keywords regarding ASQ attributes and uses a sentiment tool to derive passengers' attitudes. Through sentiment analysis, Google Maps reviews show more positive sentiment toward environment and personnel but remain constant about facilities during COVID-19. The lexical salience-valence analysis (LSVA) is then applied to explain such changes by tracking the sentiment of frequent words in reviews. Through correlation and regression analysis, this study demonstrates that rating is significantly related to check-in, environment, and personnel in pre-and post-COVID periods. Additionally, the effect of access, wayfinding, facilities, and environment on rating significantly differs between the two periods. The findings illustrate the effectiveness of leveraging online reviews and offer practical implications for what matters to air travelers, especially in the COVID-19 context.

Textual variations affect human judgements of sentiment values

• Text variations like letter repetition, letter capitalization, emoticon, different punctuations are found to have additional sentiment value compare to the plain text. • People tend to use text variations to express their emotions within text. • Text variations can play a significant role in affecting the interpretation of text reviews. • Current sentiment tools should take into consideration different text variations. Electronic word-of-mouth communication in the form of online reviews influences people’s product or service choices. People use text features to add or emphasise feelings and emotions in their text. The text emphasis can come in as capital letters, letter repetition, exclamation marks and emoticons. The existing literature has not paid sufficient attention to the effects of such textual variations on human text interpretation. This paper presents an analysis of text variations that can affect the interpretation of a text. A total of 1,041 online comments were collected, in which seven types of the most used textual variations were identified and simulated for hypothesis testing. Sentiment scores from 500 participants were collected to rate the value expressed for each of the textual variations. Statistical analysis showed that collected ratings are significant for the accurate calculation of sentiment values for short comments. Furthermore, the performance of ten existing sentiment tools was analysed based on seven textual variations. Results indicate that those tools should consider these textual variations to fully reflect a human interpretation on the text variations.

A comparative study of the effectiveness of sentiment tools and human coding in sarcasm detection

PurposeSarcasm is often used in everyday speech and writing and is prevalent in online contexts. The purpose of this paper is to investigate the analogy between sarcasm comments from sentiment tools and the human coder.Design/methodology/approachUsing the Verbal Irony Procedure, eight human coders were engaged to analyse comments collected from an online commercial page, and a dissimilarity analysis was conducted with sentiment tools. Three constants were tested, namely, polarity from sentiment tools, polarity rating by human coders; and sarcasm-level ratings by human coders.FindingsResults found an inconsistent ratio between these three constants. Sentiment tools used did not have the capability or reliability to detect the subtle, contextualized meanings of sarcasm statements that human coders could detect. Further research is required to refine the sentiment tools to enhance their sensitivity and capability.Practical implicationsWith these findings, it is recommended that further research and commercialization efforts be directed at improving current sentiment tools – for example, to incorporate sophisticated human sarcasm texts in their analytical systems. Sarcasm exists frequently in media, politics and human forms of communications in society. Therefore, more highly sophisticated sentiment tools with the abilities to detect human sarcasm would be vital in research and industry.Social implicationsThe findings suggest that presently, of the sentiment tools investigated, most are still unable to pick up subtle contexts within the text which can reverse or change the message that the writer intends to send to his/her receiver. Hence, the use of the relevant hashtags (e.g. #sarcasm; #irony) are of fundamental importance in detection tools. This would aid the evaluation of product reviews online for commercial usage.Originality/valueThe value of this study lies in its original, empirical findings on the inconsistencies between sentiment tools and human coders in sarcasm detection. The current study proves these inconsistencies are detected between human and sentiment tools in social media texts and points to the inadequacies of current sentiment tools. With these findings, it is recommended that further research and commercialization efforts be directed at improving current sentiment tools – to incorporate sophisticated human sarcasm texts in their analytical systems. The system can then be used as a reference for psychologists, media analysts, researchers and speech writers to detect cues in the inconsistencies in behaviour and language.

Exploring patient perceptions of healthcare service quality through analysis of unstructured feedback

Mechanisms for collecting unstructured feedback (i.e., text comments) from patients of healthcare providers have become commonplace, but analysis techniques to examine such feedback have not been frequently applied in this domain. To fill this gap, we apply a text mining methodology to a large set of textual feedback of physicians by their patients and relate the textual commentary to their numeric ratings. While perceptions of healthcare service quality in the form of numeric ratings are easy to aggregate, freeform textual commentary presents more challenges to extracting useful information. Our methodology explores aggregation of the textual commentary using a topic analysis procedure (i.e., latent Dirichlet allocation) and a sentiment tool (i.e., Diction). We then explore how the extracted topic areas and expressed sentiments relate to the physicians’ quantitative ratings of service quality from both patients and other physicians. We analyze 23,537 numeric ratings plus textual feedback provided by patients of 3,712 physicians who have also been recommended by other physicians, and determine process quality satisfaction is an important driver of patient perceived quality, whereas clinical quality better reflects physician perceived quality. Our findings lead us to suggest that to maximize the usefulness of online reviews of physicians, potential patients should parse them for particular quality elements they wish to assess and interpret them within the scope of those quality elements.