International Conference and Workshop (refereed)

12. Tomoki Ito, Jose Camacho Collados, Hiroki Sakaji, Steven Schockaert,

Learning Company Embeddings from Annual Reports for Fine-grained Industry Characterization, The Second Workshop on Financial Technology and Natural Language Processing In conjunction with the 29th International Joint Conference on Artificial Intelligence, Yokohama, Japan, January, 20211, link.

11. Tomoki Ito, Kota Tsubouchi, Hiroki Sakaji, Tatsuo Yamashita and Kiyoshi Izumi, SSNN: Sentiment Shift Neural Network, SDM 2020, 2020, acceptance rate = 24.0% (75/312), link.

10. Tomoki Ito, Kota Tsubouchi, Hiroki Sakaji, Tatsuo Yamashita and Kiyoshi Izumi, Word-level Contextual Sentiment Analysis with Interpretability, AAAI 2020, acceptance rate = 20.6% (1,591/7,737). link, pdf

9. Tomoki Ito, Kota Tsubouchi, Hiroki Sakaji, Tatsuo Yamashita and Kiyoshi Izumi, 

CSNN: Contextual Sentiment Neural Network, IEEE ICDM 2019, 2019, acceptance rate = 18.5% (194/1046), link

8. Tomoki Ito, Hiroki Sakaji and Kiyoshi Izumi, Segment Information Extraction From Financial Annual Reports Using Neural Network, Advances in Artificial Intelligence: Selected Papers from JSAI 2019 of the Springer Nature series Advances in Intelligent Systems and Computing, 2019, long paper, acceptance rate = 23.8% (19/80)link.

7. Tomoki Ito, Kota Tsubouchi, Hiroki Sakaji, Tatsuo Yamashita and Kiyoshi Izumi, Concept Cloud-based Sentiment Visualization for Financial Reviews, DECON 2019, 2019 

6. Tomoki Ito, Kota Tsubouchi, Hiroki Sakaji, Tatsuo Yamashita and Kiyoshi Izumi, Word-level Sentiment Visualizer for Financial Documents, IEEE CIFEr 2019, 2019. link.

5. Kei Nakagawa, Tomoki Ito, Masaya Abe, Kiyoshi Izumi, Deep Recurrent Factor Model: Interpretable Non-Linear and Time-Varying Multi-Factor Model, AAAI-19 Workshop on Network Interpretability for Deep Learning, Hawaii, US, January 2019

4. Tomoki Ito, Hiroki Sakaji, Kota Tsubouchi, Kiyoshi Izumi, and Tatsuo Yamashita, Text-visualizing Neural Network Model: Understanding Online Financial Textual Data, PAKDD 2018, Melbourne, Australia, 2018, long presentation, acceptance rate = 9.63 % (57/592). linkSupplementary.

3. Tomoki Ito, Hiroki Sakaji, Kiyoshi Izumi, Kota Tsubouchi, Tatsuo Yamashita, Development of Sentiment Indicators Using both Unlabeled and Labeled Posts, The 2017 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), pp.314-321, Hawaii, USA, November 2017.

2. Tomoki Ito, Hiroki Sakaji, Kiyoshi Izumi, Kota Tsubouchi, Tatsuo Yamashita, Development of an Interpretable Neural Network Model for Creation of Polarity Concept Dictionaries, The 2017 IEEE International Conference on Data Mining Ph. D Forum, New Orleans, USA, November 2017.

1. Tomoki Ito, Kiyoshi Izumi, Kota Tsubouchi and Tatsuo Yamashita, Polarity propagation of financial terms for market trend analyses using news articles, Proceedings of IEEE Congress on Evolutionary Computation 2016 (CEC 2016), 2016. 

Journal (refereed)

1. Tomoki Ito, Kota Tsubouchi, Hiroki Sakaji, Tatsuo Yamashita, Kiyoshi Izumi, Contextual Sentiment Neural Network for Document Sentiment Analysis, Data Science and Engineering, Springer,, 2020.

2. Tomoki Ito, Hiroki Sakaji, Kiyoshi Izumi, Kota Tsubouchi, Tatsuo Yamashita, GINN: Gradient Interpretable Neural Networks for Visualizing Financial Texts, International Journal of Data Science and Analytics, 2018.

3. Zhouhao Wang, Enda Liu, Hiroki Sakaji, Tomoki Ito, Kiyoshi Izumi, Kota Tsubouchi, Tatsuo Yamashita, Estimation of Cross-Lingual News Similarities Using Text-Mining Methods, Journal of Risk and Financial Management, Vol.11, No.1, 2018. doi:10.3390/jrfm11010008

Domestic Conference (not refereed)

8. 伊藤友貴, 坪内孝太, 山下達雄, 坂地泰紀, 和泉潔, "解釈可能なニューラルネットワークによるレビュー可視化", 言語処理学会第26回年次大会 (NLP2020), Mar., 2020.

7. 伊藤友貴, 坪内孝太, 坂地泰紀, 山下達雄, 和泉潔, "極性反転ニューラルネット", 第12回データ工学と情報マネジメントに関するフォーラム(DEIM), Mar., 2020.

6. Tomoki Ito, Hiroki Sakaji, Kiyoshi Izumi, Extraction of Business Contents from Financial Reports Using Recurrent Neural Network Model, 2019年度 人工知能学会全国大会(第33回), 2019年6月7日, 新潟

5. 伊藤友貴, 坂地泰紀, 和泉潔, 深層学習を用いた経済テキスト可視化の検証, 人工知能学会第20回金融情報学研究会, pp.61-66, 2018.

4. 伊藤友貴, 小林暁雄, 関根聡, 決算短信からの事業セグメント情報抽出, 言語処理学会第24回年次大会(NLP2018), 2018年3月13日, 岡山

3. 伊藤友貴,坪内孝太,山下達雄,和泉潔, テキスト情報から生成された極性辞書を用いた市場動向分析, 2017年度 人工知能学会全国大会(第31回) , 2017年5月24日, 名古屋

2. 伊藤友貴,坪内孝太,山下達雄,和泉潔, 経済テキストデータを用いた極性概念辞書構築とその応用,第18回人工知能学会金融情報学研究会, 2017年3月10日,東京, 2016年度 学生優秀論文賞

1. 伊藤 友貴 坪内 孝太 山下 達雄 和泉 潔, ニュース記事を用いた経済専門用語のクラスタリングと極性付与, 2016年度 人工知能学会全国大会, 2016年6月6日(月)-6月9(木) 北九州

Journal and Others

1. 和泉潔, 坂地泰紀, 伊藤友貴, 伊藤諒, 金融テキストマイニングの最新技術動向, 証券アナリストジャーナル, pp.28-36, Vol.55, No.10, 2017.

2. Enda Liu; Tomoki Ito; Kiyoshi Izumi; Kota Tsubouchi; Tatsuo Yamashita, Extraction of Bi-graph Structures Among Multilingual Financial Words Using Text-Mining Methods, in "Economic Foundations for Social Complexity Science: Theory, Sentiments, and Empirical Laws", pp. 179-191, Springer, 2017. doi="10.1007/978-981-10-5705-2_9"


1. JSPS Research Fellow Grant Number JP17J04768.DC1 (2017.4–2020.3), 10,000,000 yen


1. DEIM 2020 Online Presentation Award

2. AAAI 2020 Student Scholarship

3. PAKDD 2018 Student Travel Award, 400 US dollars 

4. 人工知能学 金融情報学研究会(SIG-FIN)2016年度 学生優秀論文賞


Program Committee

  1. COLING 2020 Industrial Track
  2. ECML PKDD 2019