Contextual Sentence Analysis for the Sentiment Prediction on Financial Data

Newsletters and social networks can reflect opinions about individual stocks from the perspective of analysts and the general public on their products and/or services. Therefore, sentiment analysis of these texts can provide useful information to help investors make investment decisions. In this paper, a hierarchical stack of Transformers model is proposed to identify the sentiment associated with companies and stocks, by predicting a score (of data type real) in a range between -1 and +1. Specifically, we fine-tuned a RoBERTa model to process headlines and microblogs. Furthermore, we combined it with additional Transformer layers to process the sentence analysis with sentiment dictionaries to improve the sentiment analysis. We evaluated it on financial data released by SemEval-2017 task 5. Our proposition outperformed the best systems of SemEval-2017 task 5 and strong baselines. We verified that the combination of contextual sentence analysis with the financial and general sentiment dictionaries indeed provided useful information to our model and allowed it to generate more reliable sentiment scores.

[1]  Pushpak Bhattacharyya,et al.  IITP at SemEval-2017 Task 5: An Ensemble of Deep Learning and Feature Based Models for Financial Sentiment Analysis , 2017, *SEMEVAL.

[2]  Véronique Hoste,et al.  Fine-grained analysis of explicit and implicit sentiment in financial news articles , 2015, Expert Syst. Appl..

[3]  Philip S. Yu,et al.  BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis , 2019, NAACL.

[4]  Finn Årup Nielsen,et al.  A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs , 2011, #MSM.

[5]  R. Goonatilake.  The Volatility of the Stock Market and News , 2007 .

[6]  Marco Guerini,et al.  Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines , 2017, *SEMEVAL.

[7]  Andrea Esuli,et al.  SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining , 2010, LREC.

[8]  Srikumar Krishnamoorthy,et al.  Sentiment analysis of financial news articles using performance indicators , 2017, Knowledge and Information Systems.

[9]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[10]  Paolo Rosso,et al.  SemEval-2015 Task 11: Sentiment Analysis of Figurative Language in Twitter , 2015, *SEMEVAL.

[11]  Eraldo Rezende Fernandes,et al.  BERT for Stock Market Sentiment Analysis , 2019, 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI).

[12]  Chung-Chi Chen,et al.  NTUSD-Fin: A Market Sentiment Dictionary for Financial Social Media Data Applications , 2018 .

[13]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[14]  Man Lan,et al.  ECNU at SemEval-2017 Task 5: An Ensemble of Regression Algorithms with Effective Features for Fine-Grained Sentiment Analysis in Financial Domain , 2017, SemEval@ACL.

[15]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[16]  Antoine Doucet,et al.  Alleviating Digitization Errors in Named Entity Recognition for Historical Documents , 2020, CONLL.

[17]  T. T. Mirnalinee,et al.  SSN_MLRG1 at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis Using Multiple Kernel Gaussian Process Regression Model , 2017, *SEMEVAL.

[18]  Thomas Wolf,et al.  DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter , 2019, ArXiv.

[19]  André Freitas,et al.  SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News , 2017, *SEMEVAL.

[20]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[21]  Siegfried Handschuh,et al.  Social sentiment indices powered by X-scores , 2016, Big Data 2016.

[22]  Preslav Nakov,et al.  SemEval-2017 Task 4: Sentiment Analysis in Twitter , 2017, *SEMEVAL.

[23]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[24]  M. Bradley,et al.  Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings , 1999 .

[25]  Martin Tutek,et al.  TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news , 2017, *SEMEVAL.

[26]  Thamar Solorio,et al.  RiTUAL-UH at SemEval-2017 Task 5: Sentiment Analysis on Financial Data Using Neural Networks , 2017, *SEMEVAL.

[27]  Jacobo Rouces,et al.  Aspect-Based Sentiment Analysis using BERT , 2019, NODALIDA.