Lexicon Creation for Financial Sentiment Analysis Using Network Embedding
- 1 School of Engineering, the University of Tokyo, Tokyo, Japan
- 2 School of Engineering, the University of Tokyo, Tokyo, Japan
- 3 School of Engineering, the University of Tokyo, Tokyo, Japan
- 4 Mitsubishi UFJ Trust Investment Technology Institute Co. Ltd., Tokyo, Japan
Abstract
In this study, we aim to construct a polarity dictionary specialized for the analysis of financial policies. Based on an idea that polarity words are likely located in the secondary proximity in the dependency network, we proposed an automatic dictionary construction method using secondary LINE (Large-scale Information Network Embedding) that is a network representation learning method to quantify relationship. The results suggested the possibility of constructing a dictionary using distributed representation by LINE. We also confirmed that a distributed representation with a property different from the distributed representation by the CBOW (Continuous Bag of Word) model was acquired and analyzed the differences between the distributed representation using LINE and the distributed representation using the CBOW model.
- Bollen, J. and Huina, M. (2011) Twitter Mood as a Stock Market Predictor. Computer, 44, 91-94.
- Curran, J.R., Murphy, T. and Scholz, B. (2007) Minimising Semantic Drift with Mutual Exclusion Bootstrapping. In Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, University of Melbourne, Australia, Sep 19-21 2007, 172-180.
- Ito, R., Suda, S. and Izumi, K. (2017) Impact Analysis of Forward Guidance on Market Expectation—Text Mining Approach—46th Winter JAFEE Competition of 2016, Musashi University, Tokyo, Japan, Feb 17-18 2017, 60-71.
- Izumi, K., Suzuki, H. and Toriumi F. (2017) Transfer Entropy Analysis of Information Flow in a Stock Market. In: Aruka, Y. and Kirman, A., Eds., Economic Foundations for Social Complexity Science: Theory, Sentiments and Empirical Laws, Springer, Berlin.
- Jegadeesh, N. and Wu, D. (2015) Deciphering Fedspeak: The Information Content of FOMC Meetings, 2016 AFA Anual Meeting Working Paper. San Francisco Marriott Marquis, San Francisco, USA, Jan 03-05 2016. https://www.aeaweb.org/conference/2016/retrieve.php?pdfid=1136
- Kamps, J., Marx, M., Mokken, R.J. and de Rijke, M. (2004) Using WordNet to Measure Semantic Orientations of Adjectives. In Proceedings of the 4th International Conference on Language Resources and Evaluation, Universidade Nova de Lisboa, Lisbon, Portugal, May 26-28 2004, 1115-1118.
- Katakura, K. and Takahashi, O. (2015) Dictionary Preparation and Financial Market Analysis by Distributed Representation Learning of Financial Market News. The 2015 National Conference of Artificial Intelligence (No. 29), Hyatt Regency Austin, Texas, USA, Jan 25-30 2015.
- Loughran, T. and McDonald, B. (2011) When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks. Journal of Finance, 66, 35-65.
- Mikolov, T., Chen, K., Corrado, G. and Dean, J. (2013) Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv: 1301.3781.
- Maaten, L.V.D., and Hinton, G. (2008) Visualizing Data Using t-SNE. Journal of Machine Learning Research, 9, 2579-2605.
- Nguyen, K.A., Walde, S.S.I. and Vu, N.T. (2016) Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, 7-12 August 2016, 454-459. https://doi.org/10.18653/v1/P16-2074