Paper: arXiv 2409.20397

Authors: Fabian Billert, Stefan Conrad

Abstract

We extract the sentiment from german and english news articles on companies in the DAX40 stock market index and use it to create a sentiment-powered pendant. Comparing it to existing products which adjust their weights at pre-defined dates once per month, we show that our index is able to react more swiftly to sentiment information mined from online news. Over the nearly 6 years we considered, the sentiment index manages to create an annualized return of 7.51% compared to the 2.13% of the DAX40, while taking transaction costs into account. In this work, we present the framework we employed to develop this sentiment index.

Complexity vs Empirical Score

  • Math Complexity: 4.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.0: no out-of-sample test; see penalty flags)
  • Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 7.0)

Why this score: The paper applies established NLP and convex optimization techniques (low advanced math) but demonstrates strong empirical rigor with a 6-year backtest on real news data, transaction costs, and a live benchmark comparison.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Create a Sentiment-Driven<br>DAX40 Performance Index"] --> B["Data Collection<br>German & English News Articles"]
  B --> C["Methodology<br>Deep Learning Sentiment Extraction<br>Company Stock Linkage"]
  C --> D["Computation<br>Rebalancing & Weight Calculation<br>Transaction Cost Deduction"]
  D --> E["Benchmarking<br>vs. Standard DAX40 (2.13% return)"]
  E --> F["Key Outcomes<br>7.51% Annualized Return<br>Faster Market Reaction"]

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 framework to extract sentiment from news headlines and convert it into weights for a sentiment‑driven performance index for the DAX40.

Source sentence
In this work, we present the framework we employed to develop this sentiment index.

Assumes 6

  • Penalty factor for transaction costs is set to 1 (one polarity). model
    Source sentence
    In order to trade only for signigifant sentiment changes, we set the penalty factor to 1, which is one polarity.
  • Maximum weight per single company is limited to 10% of the portfolio. execution
    Source sentence
    As for constraints, we decide to limit the total investment in a single company to 10%.
  • Sum of portfolio weights must be between 99% and 99.9% (effectively 100%). execution
    Source sentence
    we instead require the sum of weights to be between 99% and 99.9%
  • Transaction costs are 0.05% of the stock price per trade. execution
    Source sentence
    We set the trading costs to 0.05% of the price of the stock, which is multiplied with the amount of stocks traded to get the total cost of a transaction.
Show 2 more
  • German news articles are translated to English before sentiment classification. data
    Source sentence
    Rather than using two separate models or retraining the model as a multilanguage model, we translated the german articles to english before classifying their sentiment.
  • Balanced accuracy of the sentiment model is 67% for English and 65% for translated German articles. model
    Source sentence
    We found that for the english articles, we achieve a balanced accuracy of 67%, while for the german-to-english translated articles we still achieve 65%.

Data

Backtest sample: DAX40 · equities · daily

  • News headlines (German and English) on DAX40 companies text-news unknown
    DAX40 constituents
    Source sentence
    We extract the sentiment from german and english news articles on companies in the DAX40 stock market index
  • Financial Phrasebank dataset · Malo et al. 2014 text-news public
    Source sentence
    ... and was fine‑tuned first with the Financial Phrasebank dataset from (Malo et al. 2014)
  • Manually annotated financial news headlines text-news unknown
    Source sentence
    and then again with manually annotated financial news headlines

Recognised sources: Financial PhraseBank

Costs

Modeled Costs are part of the reported headline results.

Trading costs are set to 0.05% of the stock price per transaction.

Source sentence
We set the trading costs to 0.05% of the price of the stock, which is multiplied with the amount of stocks traded to get the total cost of a transaction.

Finds 3

Reported performance (sentiment index): annual return 7.5%

  • The sentiment index achieved an annualized return of 7.51% over the 6‑year period, compared to 2.13% for the DAX40 benchmark. performance
    Source sentence
    Over the nearly 6 years we considered, the sentiment index manages to create an annualized return of 7.51% compared to the 2.13% of the DAX40, while taking transaction costs into account.
  • The sentiment‑driven index outperforms the DAX40 after 2018, showing higher cumulative performance despite similar results in 2017‑2018. performance
    Source sentence
    We can see that the sentiment index shows a similar performance in 2017 and 2018, but manages to outpace the DAX in the following...
  • The proposed framework enables weight adjustments at any point in time without incurring large transaction costs, unlike existing monthly‑rebalanced products. theoretical
    Source sentence
    our more flexible approach which is able to change the constituent weights at any point in time without amassing large amounts of transaction costs.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 13 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 (229)

  1. GL-GCN: Global and Local Dependency Guided Graph Convolutional Networks for aspect-based sentiment classification (2021) — link
  2. Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey (2021) — link
  3. The Effects of Twitter Sentiment on Stock Price Returns (2015) — link
  4. German’s Next Language Model (2020) — link
  5. Good debt or bad debt: Detecting semantic orientations in economic texts (2014) — link
  6. Improving Language Understanding by Generative Pre-Training (2018)
  7. Web Media and Stock Markets : A Survey and Future Directions from a Big Data Perspective (02.2018) — link
  8. Sentiment indices and stock returns: Evidence from China (2021) — link
and 221 more
  1. How does Punctuation Affect Neural Models in Natural Language Inference — link
  2. Learning Tone and Attribution for Financial Text Mining (2016)
  3. The Effect of Social Media on Market Liquidity (2015) — link
  4. What is this article about? Generative summarization with the BERT model in the geosciences domain (2022) — link
  5. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (2019) — link
  6. A tale of two sentiment scales: Disentangling short-run and long-run components in multivariate sentiment dynamics (2019) — link
  7. Data Preprocessing for Efficient Sentimental Analysis (2018) — link
  8. Aggregation of Sentiment Analysis Index with Hesitant Fuzzy Sets for Financial Time Series Forecasting (2021) — link
  9. A dataset for Sentiment analysis of Entities in News headlines (SEN) (2021) — link
  10. MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer (2020) — link
  11. Machine Learning Classification Methods and Portfolio Allocation: An Examination of Market Efficiency (2020) — link
  12. Public Mood–Driven Asset Allocation: the Importance of Financial Sentiment in Portfolio Management (2018) — link
  13. Sentiment and Knowledge Based Algorithmic Trading with Deep Reinforcement Learning (2020) — link
  14. Machine learning portfolio allocation (2022) — link
  15. Leveraging Social Media to Predict Continuation and Reversal in Asset Prices (2021) — link
  16. An Entity-Driven Framework for Abstractive Summarization (2019) — link
  17. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019) — link
  18. Transformers generalize differently from information stored in context vs in weights (2022) — link
  19. The Cross‐Section of Expected Stock Returns (1992) — link
  20. Universal Language Model Fine-tuning for Text Classification (2018) — link
  21. A picture is worth a thousand words: Measuring investor sentiment by combining machine learning and photos from news (2021) — link
  22. Causally Estimating the Sensitivity of Neural NLP Models to Spurious Features (2021) — link
  23. Deep learning for time series classification: a review (2019) — link
  24. Explanation-Based Human Debugging of NLP Models: A Survey (2021-12) — link
  25. Re-Evaluating GermEval17 Using German Pre-Trained Language Models (2021) — link
  26. Stock Price Prediction Using Sentiment Analysis (2021) — link
  27. FinancialBERT - A Pretrained Language Model for Financial Text Mining (2022-02) — link
  28. Deep Reinforcement Learning for Asset Allocation in US Equities (2020) — link
  29. Generalization through Memorization: Nearest Neighbor Language Models (2019) — link
  30. Sentiment analysis of financial news articles using performance indicators (2018) — link
  31. Structural Text Segmentation of Legal Documents (2020) — link
  32. Parameterized Explanations for Investor / Company Matching (2021) — link
  33. Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis (2020) — link
  34. Using four different online media sources to forecast the crude oil price (2021) — link
  35. Stance Prediction for Contemporary Issues: Data and Experiments (2020) — link
  36. Stock Movement Prediction with Financial News using Contextualized Embedding from BERT (2021) — link
  37. Training a Broad-Coverage German Sentiment Classification Model for Dialog Systems (2020) — link
  38. A Comparative Analysis of Forecasting Financial Time Series Using ARIMA, LSTM, and BiLSTM (2019) — link
  39. A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis (2019) — link
  40. Spectral analysis of time-dependent market-adjusted return correlation matrix (2018) — link
  41. Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (2019) — link
  42. Intelligent trading systems: a sentiment-aware reinforcement learning approach (2021) — link
  43. Fine-grained analysis of explicit and implicit sentiment in financial news articles (2015) — link
  44. Automatic extraction of gene-disease associations from literature using joint ensemble learning (2018) — link
  45. HHU at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Data using Machine Learning Methods (2017) — link
  46. Return Attribution (2012)
  47. Ad Headline Generation using Self-Critical Masked Language Model (2021) — link
  48. Term Expansion and FinBERT fine-tuning for Hypernym and Synonym Ranking of Financial Terms (2021) — link
  49. Attention Modeling for Targeted Sentiment (2017) — link
  50. Automated Investor Sentiment Classification using Financial Social Media (2021) — link
  51. Matching the Blanks: Distributional Similarity for Relation Learning (2019) — link
  52. S&P 500 Twitter Sentiment Index | S&P Dow Jones Indices (2021)
  53. BERT-Based Stock Market Sentiment Analysis (2020) — link
  54. A Primer on Neural Network Models for Natural Language Processing (2016) — link
  55. Semantic Frames to Predict Stock Price Movement (2013) — link
  56. Reinforcement Learning: An Introduction, by Sutton, R.S. and Barto, A.G. (1999) — link
  57. HuggingFace’s Transformers: State-of-the-art Natural Language Processing (2019) — link
  58. Market sentiment-aware deep reinforcement learning approach for stock portfolio allocation (2021) — link
  59. Universal Language Model Fine-tuning for Text Classification (2018) — link
  60. Sentiment Classification by Incorporating Background Knowledge from Financial Ontologies (2022)
  61. Design and analysis of a large-scale COVID-19 tweets dataset (2021) — link
  62. Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction (2018) — link
  63. One for “All”: a unified model for fine-grained sentiment analysis under three tasks (2021) — link
  64. exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources (2020) — link
  65. Prediction of stock values changes using sentiment analysis of stock news headlines (2021) — link
  66. CVXPY: A Python-Embedded Modeling Language for Convex Optimization (2016) — link
  67. TweetSenti: Target-dependent Tweet Sentiment Analysis (2019) — link
  68. AllenNLP: A Deep Semantic Natural Language Processing Platform (2018) — link
  69. Predicting Stock Market Indicators Through Twitter “I hope it is not as bad as I fear” (2011) — link
  70. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter (2019) — link
  71. Target-Based Sentiment Analysis using a BERT Embedded Model (2020) — link
  72. Aspect-based Sentiment Analysis in Question Answering Forums (2021) — link
  73. Neural Machine Translation of Rare Words with Subword Units (2015) — link
  74. A BERT based Sentiment Analysis and Key Entity Detection Approach for Online Financial Texts (2021) — link
  75. Stock Price Prediction using Facebook Prophet (2022) — link
  76. Tracking Turbulence Through Financial News During COVID-19 (2021) — link
  77. INF-UFG at FiQA 2018 Task 1 (2018) — link
  78. Subjectivity detection for sentiment analysis on Twitter data (2020) — link
  79. Stock-specific sentiment and return predictability (2020) — link
  80. OPT: Open Pre-trained Transformer Language Models (2022) — link
  81. Bayesian model averaging and the conditional volatility process: an application to predicting aggregate equity returns by conditioning on economic variables (2021) — link
  82. Unsupervised Domain Clusters in Pretrained Language Models (2020) — link
  83. NumHTML: Numeric-Oriented Hierarchical Transformer Model for Multi-Task Financial Forecasting (2022) — link
  84. Graph Auto-Encoders for Financial Clustering (2021) — link
  85. BERT’s sentiment score for portfolio optimization: a fine-tuned view in Black and Litterman model (2022) — link
  86. SemEval-2014 Task 4: Aspect Based Sentiment Analysis — link
  87. Visualizing the Financial Impact of Presidential Tweets on Stock Markets (2021) — link
  88. Image–text sentiment analysis via deep multimodal attentive fusion (2019) — link
  89. Gated Neural Networks for Targeted Sentiment Analysis (2016) — link
  90. GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval (2021) — link
  91. A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing (2021) — link
  92. FinSSLx: A Sentiment Analysis Model for the Financial Domain Using Text Simplification (2018) — link
  93. Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformers (2020) — link
  94. An Entity-Level Sentiment Analysis of Financial Text Based on Pre-Trained Language Model (2020) — link
  95. Algorithmic Trading using Sentiment Analysis and Reinforcement Learning
  96. Understanding Pre-trained BERT for Aspect-based Sentiment Analysis (2020) — link
  97. Contextual Sentence Analysis for the Sentiment Prediction on Financial Data (2021) — link
  98. Sentiment correlation in financial news networks and associated market movements (2021) — link
  99. SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News (2017) — link
  100. Long Short-Term Memory-Networks for Machine Reading (2016) — link
  101. Convolutional Neural Networks for Sentence Classification (2014) — link
  102. Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016) — link
  103. Adverse Media Mining for KYC and ESG Compliance (2021) — link
  104. Portfolio Optimization with 2D Relative-Attentional Gated Transformer (2020) — link
  105. Contextual String Embeddings for Sequence Labeling (2018) — link
  106. Automatic Generation of Product Association Networks Using Latent Dirichlet Allocation (2011) — link
  107. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019) — link
  108. Attention Is All You Need (2017) — link
  109. How to Fine-Tune BERT for Text Classification? (2020) — link
  110. Quantile connectedness between sentiment and financial markets: Evidence from the S&P 500 twitter sentiment index (2022) — link
  111. Daily market news sentiment and stock prices (2019) — link
  112. Stock Market Prediction using Recurrent Neural Network’s LSTM Architecture (2021) — link
  113. Insights of strength and weakness of evolving methodologies of sentiment analysis (2021) — link
  114. Parameter-Efficient Transfer Learning for NLP (2019) — link
  115. Disagreement after News: Gradual Information Diffusion or Differences of Opinion? (2021) — link
  116. LSTM Architecture for Oil Stocks Prices Prediction (2022) — link
  117. Deep Residual Learning for Image Recognition (2015) — link
  118. NewsMTSC: A Dataset for (Multi-)Target-dependent Sentiment Classification in Political News Articles (2021) — link
  119. The “Sixth” Factor— A Social Media Factor Derived Directly from Tweet Sentiments (2017) — link
  120. Inside the Mind of Investors During the COVID-19 Pandemic: Evidence from the StockTwits Data (2020) — link
  121. Aspect-Based Sentiment Analysis using BERT — link
  122. Predicting Stock Movement Using Sentiment Analysis of Twitter Feed with Neural Networks (2020) — link
  123. A rewriting system for convex optimization problems (2018) — link
  124. Investigating the Performance of Fine-tuned Text Classification Models Based-on Bert (2020) — link
  125. Content analysis of business communication: introducing a German dictionary (2019) — link
  126. Time horizon-aware modeling of financial texts for stock price prediction (2021) — link
  127. Stock Price Prediction via Discovering Multi-Frequency Trading Patterns (2017) — link
  128. Pointer Networks (2015) — link
  129. SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods (2016) — link
  130. Analysis of News and Stock Market with FinBERT models (2022) — link
  131. TweetsCOV19 - A Knowledge Base of Semantically Annotated Tweets about the COVID-19 Pandemic (2020) — link
  132. An Effective Domain Adaptive Post-Training Method for BERT in Response Selection (2020) — link
  133. Financial Aspect-Based Sentiment Analysis using Deep Representations (2018) — link
  134. Leveraging BERT to Improve the FEARS Index for Stock Forecasting (2019) — link
  135. BUZZ - VanEck Social Sentiment ETF (2021)
  136. Interdependency between the Stock Market and Financial News (2019) — link
  137. FinEAS: Financial Embedding Analysis of Sentiment (2021) — link
  138. AdapterFusion: Non-Destructive Task Composition for Transfer Learning (2020) — link
  139. FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining (2020) — link
  140. BERTopic: Neural topic modeling with a class-based TF-IDF procedure (2022) — link
  141. The Capital Asset Pricing Model: Theory and Evidence (2004) — link
  142. A Numerical-Based Attention Method for Stock Market Prediction With Dual Information (2019) — link
  143. Competition among memes in a world with limited attention (2012) — link
  144. FinBERT: A Pretrained Language Model for Financial Communications (2020) — link
  145. A Stochastic Time Series Model for Predicting Financial Trends using NLP (2021) — link
  146. Portfolio Optimization-Based Stock Prediction Using Long-Short Term Memory Network in Quantitative Trading (2020) — link
  147. A Five-Factor Asset Pricing Model (2014) — link
  148. Beyond facts – a survey and conceptualisation of claims in online discourse analysis (2022) — link
  149. News-based business sentiment and its properties as an economic index (2022) — link
  150. A Primer in BERTology: What We Know About How BERT Works (2021) — link
  151. CNNPred: CNN-based stock market prediction using several data sources (2018) — link
  152. An automated portfolio trading system with feature preprocessing and recurrent reinforcement learning (2021) — link
  153. Neural Network Predictive Modeling on Dynamic Portfolio Management—A Simulation-Based Portfolio Optimization Approach (2020) — link
  154. A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem (2017) — link
  155. Artificial Intelligence Applied to Stock Market Trading: A Review (2021) — link
  156. Feature Investigation for Stock Returns Prediction Using XGBoost and Deep Learning Sentiment Classification and Deep Learning Sentiment Classification (2021)
  157. What to Pre-Train on? Efficient Intermediate Task Selection (2021) — link
  158. Choosing news topics to explain stock market returns (2020) — link
  159. Sentiment in German-language News and Blogs, and the DAX
  160. Statistical and Machine Learning forecasting methods: Concerns and ways forward (2018) — link
  161. ERNIE: Enhanced Language Representation with Informative Entities (2019) — link
  162. Stock Price Prediction Under Anomalous Circumstances (2020) — link
  163. AdapterHub: A Framework for Adapting Transformers (2020) — link
  164. Defending Against Neural Fake News (2019) — link
  165. Brazilian stock market performance and investor sentiment on Twitter (2022) — link
  166. Learning to Determine the Quality of News Headlines (2020) — link
  167. SciBERT: A Pretrained Language Model for Scientific Text (2019) — link
  168. Language Models are Unsupervised Multitask Learners
  169. Exploring user historical semantic and sentiment preference for microblog sentiment classification (2021) — link
  170. On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation (2021) — link
  171. Stock Price Predictions with LSTM Neural Networks and Twitter Sentiment (2021) — link
  172. Social media and firm equity value (2013) — link
  173. AdapterDrop: On the Efficiency of Adapters in Transformers (2020) — link
  174. Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing (2022) — link
  175. XLNet: Generalized Autoregressive Pretraining for Language Understanding (2019) — link
  176. Facebook FAIR’s WMT19 News Translation Task Submission (2019) — link
  177. From Opinion Mining to Financial Argument Mining (2021) — link
  178. Misleading the Covid-19 vaccination discourse on Twitter: An exploratory study of infodemic around the pandemic (2021) — link
  179. HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (2022) — link
  180. Handbook of Natural Computing (2012) — link
  181. Target-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis (2020) — link
  182. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2018) — link
  183. Prefix-Tuning: Optimizing Continuous Prompts for Generation (2021) — link
  184. Sentiment Analysis — Comparing 3 Common Approaches: Naive Bayes, LSTM, and VADER | by Kevin C Lee | Towards Data Science — link
  185. Bayesian Topic Regression for Causal Inference (2021) — link
  186. S&P 500 Twitter Sentiment Select Equal Weight Index | S&P Dow Jones Indices (2021)
  187. Exploiting BERT for Multimodal Target Sentiment Classification through Input Space Translation (2021) — link
  188. Deep learning-based feature engineering for stock price movement prediction (2019) — link
  189. Stock Price Prediction Using News Sentiment Analysis (2019) — link
  190. Recent Advances in Reinforcement Learning in Finance (2021) — link
  191. Stock movement predictive network via incorporative attention mechanisms based on tweet and historical prices (2020) — link
  192. Crude oil price forecasting incorporating news text (2020) — link
  193. Effective Approaches to Attention-based Neural Machine Translation (2015) — link
  194. Investors’ mood and herd investing: a quantile-on-quantile regression explanation from crypto market (2021) — link
  195. LSTM-based sentiment analysis for stock price forecast (2021) — link
  196. Stock Movement Prediction from Tweets and Historical Prices (2018) — link
  197. FinBERT: Financial Sentiment Analysis with Pre-trained Language Models (2019) — link
  198. It’s a New Era of Investing. Welcome to BUZZ. - BUZZ Indexes (2021)
  199. Stock Price Movement Prediction Using Sentiment Analysis and CandleStick Chart Representation. (2021) — link
  200. Entity-Aware Abstractive Multi-Document Summarization (2021) — link
  201. Zero-Shot Aspect-Based Sentiment Analysis (2022) — link
  202. Target-dependent Twitter Sentiment Classification — link
  203. Advances in Intelligent Data Analysis XX, 20th International Symposium on Intelligent Data Analysis, IDA 2022, Rennes, France, April 20–22, 2022, Proceedings (2022) — link
  204. PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization (2019) — link
  205. Sentiment Analysis for Fake News Detection (2021) — link
  206. Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers (2021) — link
  207. A machine learning approach to detect early signs of startup success (2021) — link
  208. Fusion of Sentiment and Asset Price Predictions for Portfolio Optimization (2022) — link
  209. Evaluating the Rationales of Amateur Investors (2021) — link
  210. Narrative and computational text analysis in business and economic history (2021) — link
  211. Front Page News: The Effect of News Positioning on Financial Markets (Working Paper)
  212. Forecasting the CNY-CNH pricing differential: The role of investor attention (2018) — link
  213. Impact of Public News Sentiment on Stock Market Index Return and Volatility (2021) — link
  214. Stock price prediction using BERT and GAN (2021) — link
  215. FinBERT—A Deep Learning Approach to Extracting Textual Information (2020) — link
  216. Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks (2020) — link
  217. Identifying the influential factors of commodity futures prices through a new text mining approach (2020) — link
  218. Learning and Evaluating General Linguistic Intelligence (2019) — link
  219. Hybrid Deep Learning Models for Sentiment Analysis (2021) — link
  220. Reformer: The Efficient Transformer (2020) — link
  221. The Effect of Preprocessing Techniques on Twitter Sentiment Analysis (2016) — link

0 of 229 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.