Paper: arXiv 2404.08665

Authors: Silvia García-Méndez, Francisco de Arriba-Pérez, Ana Barros-Vila, Francisco J. González-Castaño

Abstract

Microblogging platforms, of which Twitter is a representative example, are valuable information sources for market screening and financial models. In them, users voluntarily provide relevant information, including educated knowledge on investments, reacting to the state of the stock markets in real-time and, often, influencing this state. We are interested in the user forecasts in financial, social media messages expressing opportunities and precautions about assets. We propose a novel Targeted Aspect-Based Emotion Analysis (TABEA) system that can individually discern the financial emotions (positive and negative forecasts) on the different stock market assets in the same tweet (instead of making an overall guess about that whole tweet). It is based on Natural Language Processing (NLP) techniques and Machine Learning streaming algorithms. The system comprises a constituency parsing module for parsing the tweets and splitting them into simpler declarative clauses; an offline data processing module to engineer textual, numerical and categorical features and analyse and select them based on their relevance; and a stream classification module to continuously process tweets on-the-fly. Experimental results on a labelled data set endorse our solution. It achieves over 90% precision for the target emotions, financial opportunity, and precaution on Twitter. To the best of our knowledge, no prior work in the literature has addressed this problem despite its practical interest in decision-making, and we are not aware of any previous NLP nor online Machine Learning approaches to TABEA.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper employs NLP and streaming ML algorithms with specific experimental results (90% precision) on a labeled dataset, indicating strong empirical implementation, but the mathematical complexity is moderate, focusing on applied algorithms rather than novel theoretical derivations.

Research Flowchart

  flowchart TD
  A["Research Goal"] --> B["Input: Financial Tweets"]
  A --> C["Constituency Parsing"]
  B --> D["Offline Data Processing"]
  C --> D
  D --> E["Stream Classification"]
  E --> F["Outcomes >90% Precision"]
  E --> G["Outcomes: Opportunity & Precaution Detection"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a novel Targeted Aspect-Based Emotion Analysis (TABEA) system for detecting financial opportunity and precaution emotions in Twitter messages.

Source sentence
We propose a novel Targeted Aspect-Based Emotion Analysis (TABEA) system that can individually discern the financial emotions (positive and negative forecasts) on the different stock market assets in the same tweet (instead of making an overall guess about that whole tweet).

Assumes

No explicit assumptions found in the text.

Data

  • experimental data set text-news unknown
    Source sentence
    Table 5 shows the resulting distribution of the segments in the experimental data set by emotion category tag.

Recognised sources: Twitter / X Yahoo Finance

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • The system achieves over 90% precision for the target emotions (opportunity and precaution) on Twitter. predictive-accuracy
    Source sentence
    It achieves over 90% precision for the target emotions, financial opportunity, and precaution on Twitter.
  • The stacked random‑forest classifier attains around 85% accuracy, over 90% precision and about 75% recall for both financial precautions and opportunities. performance
    Source sentence
    Consequently, we consider the rf classifier the best choice in our scenario, attaining around 85% accuracy, over 90% precision and around 75% recall both for financial precautions and opportunities.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 9 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (108)

  1. Predictors of investment intention in Indian stock markets (2019) — link
  2. Emotion Analysis and Dialogue Breakdown Detection in Dialogue of Chat Systems Based on Deep Neural Networks (2022) — link
  3. Convolutional attention neural network over graph structures for improving the performance of aspect-level sentiment analysis (2022) — link
  4. Exploring fine-grained syntactic information for aspect-based sentiment classification with dual graph neural networks (2022) — link
  5. Aspect-Based Sentiment Analysis With Heterogeneous Graph Neural Network (2022) — link
  6. Aggregated graph convolutional networks for aspect-based sentiment classification (2022) — link
  7. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2022) — link
  8. Deep learning approach to text analysis for human emotion detection from big data (2022) — link
and 100 more
  1. Consensus vote models for detecting and filtering neutrality in sentiment analysis (2018) — link
  2. The concept of neutrality: a new approach (2019) — link
  3. Multi-Level Fine-Scaled Sentiment Sensing with Ambivalence Handling (2020) — link
  4. Semantics of the Black-Box: Can Knowledge Graphs Help Make Deep Learning Systems More Interpretable and Explainable? (2021) — link
  5. Aspect-Based Extraction and Analysis of Affective Knowledge from Social Media Streams (2017) — link
  6. GSMNet: Global Semantic Memory Network for Aspect-Level Sentiment Classification (2021) — link
  7. SenticNet 7: a commonsense-based neurosymbolic AI framework for explainable sentiment analysis (2022)
  8. Big Data: Deep Learning for financial sentiment analysis (2018) — link
  9. Stochastic Gradient Descent (2021) — link
  10. Classifying streaming of Twitter data based on sentiment analysis using hybridization (2019) — link
  11. Keeping our rivers clean: Information-theoretic online anomaly detection for streaming business process events (2022) — link
  12. Online Anomaly Detection Using Statistical Leverage for Streaming Business Process Events (2021) — link
  13. Enhanced Hoeffding Anytime Tree: A Real-time Algorithm for Early Prediction of Heart Disease (2021) — link
  14. Analysis of concept drift in fake reviews detection (2021) — link
  15. Handling Concept Drift for Predictions in Business Process Mining (2020) — link
  16. Comparative Evaluation of the Supervised Machine Learning Classification Methods and the Concept Drift Detection Methods in the Financial Business Problems (2021) — link
  17. Drift-based approach for evolving data stream classification in intrusion detection system (2021)
  18. A Comparative Analysis of Machine Learning Techniques for Cyberbullying Detection on Twitter (2020) — link
  19. Opinion mining and emotion recognition applied to learning environments (2020) — link
  20. Sentiment Analysis of Tweets on Social Issues using Machine Learning Approach (2020) — link
  21. A Review on Random Forest: An Ensemble Classifier (2019) — link
  22. Decision tree classifiers for evidential attribute values and class labels (2019) — link
  23. Text Mining: Use of TF-IDF to Examine the Relevance of Words to Documents (2018) — link
  24. Emotional trading in the cryptocurrency market (2021) — link
  25. Dissecting emotion and user influence in social media communities: An interaction modeling approach (2020) — link
  26. Tales of emotion and stock in China: volatility, causality and prediction (2018) — link
  27. Mining Emotions of the Public from Social Media for Enhancing Corporate Credit Rating (2018) — link
  28. Using Deep Learning to Develop a Stock Price Prediction Model Based on Individual Investor Emotions (2021) — link
  29. How emotions influence behavior in financial markets: a conceptual analysis and emotion-based account of buy-sell preferences (2020) — link
  30. A review on sentiment analysis and emotion detection from text (2021) — link
  31. Cooperative gating network based on a single BERT encoder for aspect term sentiment analysis (2022) — link
  32. An improved aspect-category sentiment analysis model for text sentiment analysis based on RoBERTa (2021) — link
  33. A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA (2021) — link
  34. Comparing pre-trained language models for Spanish hate speech detection (2021) — link
  35. An analytical approach for big social data analysis for customer decision-making in eco-friendly hotels (2021) — link
  36. How Intense Are You? Predicting Intensities of Emotions and Sentiments using Stacked Ensemble (2020) — link
  37. Does Twitter Affect Stock Market Decisions? Financial Sentiment Analysis During Pandemics: A Comparative Study of the H1N1 and the COVID-19 Periods (2022) — link
  38. Stock market prediction using machine learning classifiers and social media news (2020) — link
  39. Analyzing DistilBERT for Sentiment Classification of Banking Financial News (2021) — link
  40. An AI-Enabled Stock Prediction Platform Combining News and Social Sensing with Financial Statements (2021) — link
  41. Predicting Business Risks of Commercial Banks Based on BP-GA Optimized Model (2021) — link
  42. The Use of Machine Learning Combined with Data Mining Technology in Financial Risk Prevention (2021) — link
  43. Estimating large losses in insurance analytics and operational risk using the g-and-h distribution (2021) — link
  44. Leveraging Social Media to Predict Continuation and Reversal in Asset Prices (2021) — link
  45. Stock index prediction based on wavelet transform and FCD‐MLGRU (2020) — link
  46. Novel dual-channel long short-term memory compressed capsule networks for emotion recognition (2022) — link
  47. Towards Emotion-aware Recommender Systems: an Affective Coherence Model based on Emotion-driven Behaviors (2021) — link
  48. COVID-19 adopted hybrid and parallel deep information fusion framework for stock price movement prediction (2022) — link
  49. Predicting Ethereum prices with machine learning based on blockchain information (2021) — link
  50. Sentiment classification and aspect-based sentiment analysis on yelp reviews using deep learning and word embeddings (2021) — link
  51. Harshness-aware sentiment mining framework for product review (2022) — link
  52. Recommendation system exploiting aspect-based opinion mining with deep learning method (2020) — link
  53. Opinion mining using ensemble text hidden Markov models for text classification (2018) — link
  54. A survey on classification techniques for opinion mining and sentiment analysis (2019) — link
  55. How Does Social Media Impact Bitcoin Value? A Test of the Silent Majority Hypothesis (2018) — link
  56. More than just Noise? Examining the Information Content of Stock Microblogs on Financial Markets (2018) — link
  57. Predicting Vehicle Sales by Sentiment Analysis of Twitter Data and Stock Market Values (2018) — link
  58. Topic sentiment mining for sales performance prediction in e-commerce (2018) — link
  59. A CNN-BiLSTM Model for Document-Level Sentiment Analysis (2019) — link
  60. Classification of sentence level sentiment analysis using cloud machine learning techniques (2019) — link
  61. Aspect-based sentiment analysis using adaptive aspect-based lexicons (2020) — link
  62. A model for sentiment and emotion analysis of unstructured social media text (2018) — link
  63. Tracking and recognizing emotions in short text messages from online chatting services (2018) — link
  64. Forecasting stock market crisis events using Deep and statistical Machine Learning techniques (2018) — link
  65. Enhancing Aspect-Based Sentiment Analysis of Arabic hotels’ reviews using morphological, syntactic and semantic features (2019) — link
  66. Targeting Prospective Customers: Robustness of Machine-Learning Methods to Typical Data Challenges (2019) — link
  67. Pachinko Prediction: A Bayesian method for event prediction from social media data (2020) — link
  68. Aspect Based Sentiment Analysis for Restaurant Reviews Using Hybrid ELMoWikipedia and Hybrid Expanded Opinion Lexicon-SentiCircle (2019) — link
  69. An approach to analyze suicidal tendency in blogs and tweets using Sentiment Analysis (2018) — link
  70. A survey of sentiment analysis in social media (2019) — link
  71. Feature engineering for sentiment analysis in e-health forums (2018) — link
  72. Word2Vec for Indonesian Sentiment Analysis towards Hotel Reviews: An Evaluation Study (2019) — link
  73. Creating Emoji Lexica from Unsupervised Sentiment Analysis of their Descriptions (2018) — link
  74. Spam comments prediction using stacking with ensemble learning (2018) — link
  75. Stacking-Based Ensemble Learning of Self-Media Data for Marketing Intention Detection (2019) — link
  76. A Lexical and Machine Learning-Based Hybrid System for Sentiment Analysis (2018) — link
  77. word2set: WordNet-Based Word Representation Rivaling Neural Word Embedding for Lexical Similarity and Sentiment Analysis (2019) — link
  78. A Hybrid Multilingual Fuzzy-Based Approach to the Sentiment Analysis Problem Using SentiWordNet (2020) — link
  79. DWWP: Domain-specific new words detection and word propagation system for sentiment analysis in the tourism domain (2018) — link
  80. Emotional finance: investment and the unconscious (2018) — link
  81. Detection of Financial Opportunities in Micro-Blogging Data With a Stacked Classification System (2020) — link
  82. Beyond negative and positive: Exploring the effects of emotions in social media during the stock market crash (2020) — link
  83. Stock Market Forecasting with Financial Micro-blog Based on Sentiment and Time Series Analysis (2017) — link
  84. Investment Decisions Based on EEG Emotion Recognition (2017) — link
  85. Automatic Natural Language Generation Applied to Alternative and Augmentative Communication for Online Video Content Services using SimpleNLG for Spanish (2018) — link
  86. A library for automatic Natural Language Generation of Spanish texts (2019) — link
  87. Content Analysis: An Introduction to its Methodology (2018) — link
  88. Assessing the efficacy of a manual‐based intervention for improving the detection of facial pain expression (2019) — link
  89. Development and accuracy of an artificial intelligence algorithm for acne grading from smartphone photographs (2019) — link
  90. Online Hate Ratings Vary by Extremes (2019) — link
  91. Toward assessing clinical trial publications for reporting transparency (2021) — link
  92. Bayes’ Theorem and Naive Bayes Classifier (2019) — link
  93. Scikit-multiflow: A Multi-output Streaming Framework (2018) — link
  94. Continuous Learning from Human Post-Edits for Neural Machine Translation (2017) — link
  95. Online Learning for Statistical Machine Translation (2016) — link
  96. Native Language Identification With Classifier Stacking and Ensembles (2018) — link
  97. The circumplex as a general model of the structure of emotions and personality (2004) — link
  98. Hotel Arabic-Reviews Dataset Construction for Sentiment Analysis Applications (2018) — link
  99. FineNews: fine-grained semantic sentiment analysis on financial microblogs and news (2019) — link
  100. What predicts student satisfaction with MOOCs: A gradient boosting trees supervised machine learning and sentiment analysis approach (2020) — link

0 of 108 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.