ECONLP 2019 – 2nd Workshop on Economics and Natural Language Processing

This workshop is collocated with EMNLP-IJCNLP 2019, Hong Kong , November 4 , 2019

This Workshop

After launching the Workshop on Economics and Natural Language Processing (ECONLP) @ ACL 2018 in Melbourne, Australia (, the 2nd edition of ECONLP will be held on November 4 in Hong Kong at EMNLP-IJCNLP 2019 (

This workshop addresses the increasing relevance of natural language processing (NLP) for regional, national and international economy, both in terms of already operational language technology products and systems, as well as newly emerging methodologies and techniques reflecting the requirements at the intersection of economics and NLP. The focus of the workshop will be on the many ways, how NLP influences business relations and procedures, economic transactions, and the roles of human and computational actors involved in commercial activities.

Workshop Organizers

Important Dates

  • Submission Deadline: Monday, August 19 Monday, August 26 (AOE)
  • Acceptance Notification: Monday, September 16 Wednesday, September 18
  • Camera-Ready: Monday, September 30
  • Workshop day: November 4 @ EMNLP-IJCNLP 2019

Submission Information

We invite two types of original and unpublished works: Long papers (8 pages) should describe solid results with strong experimental, empirical or theoretical/formal backing, short papers (4 pages) should describe work in progress where preliminary results have already been worked out. Accepted papers will appear in the workshop proceedings. All papers are allowed unlimited but sensible pages for references. Final camera-ready versions will be allowed an additional page of content to address reviewers’ comments. All submissions must be anonymized, in PDF format (using the EMNLP 2019 style sheets for the main conference; see and must be made through the Softconf website set up for this workshop (

Double Submission Policy

Papers that have been or will be submitted to other meetings or publication sites must indicate this information at submission time. However, we prohibit dual submissions among EMNLP-IJCNLP 2019 workshops. This rule does not necessarily prohibit an EMNLP-IJCNLP 2019 workshop from accepting a presentation that is presented elsewhere (if the workshop has the policy to allow that). Authors of a paper accepted for presentation must notify the workshop organizers by the camera-ready deadline as to whether the paper will be presented or withdrawn.

Call for Papers

Papers submitted to this workshop should address (not excluding other topic areas of relevance for the workshop theme):

    • NLP-based (stock) market analytics, e.g., prediction of economic performance indicators (trend prediction, performance forecasting, etc.), by analyzing verbal statements of enterprises, businesses, companies, and associated legal or administrative actors
    • NLP-based product analytics, e.g., based on social and mass media monitoring, summarizing reviews, classifying and mining complaint messages and other (non)verbal types of customer reactions to products or services
    • NLP-based customer analytics, e.g., client profiling, tracking product/company preferences, screening customer reviews or complaints, identifying high-influentials in economy-related communication networks
    • NLP-based organization/enterprise analytics (e.g., tracing and altering social images of organizational actors, risk prediction, fraud analysis, predictive analysis of annual business, sustainability and auditing reports)
    • Market sentiments and emotions as evident from consumers’ and enterprises’ verbal behavior and their communication strategies about products and services
    • Competitive intelligence services based on NLP tooling
    • Relationship and interaction between quantitative (structured) economic data (e.g., contained sales databases and associated time series data) and qualitative (unstructured verbal) economic data (press releases, newswire streams, social media contents, etc.)
    • Information management based on the content-based organization, packaging and archiving of verbal communication streams of organizations and enterprises (emails, meeting minutes, business letters, internal reporting, etc.)
    • Credibility and trust models for business agents involved in the economic process (e.g., as traders, sellers, advertisers) extracted from text/opinion mining their current communication as well as historic legacy data
    • Deceptive or fake information recognition related to economic objects (such as products, advertisements, etc.) or economic actors (such as industries, companies, etc.), including opinion spam targeting or emanating from economic actors and processes
    • Verbally fluent software agents (chat bots for sales and marketing) as reliable actors in economic processes serving business interests, e.g., embodying models of persuasion, information biases, fair trading
    • Enterprise search engines (e-commerce, e-marketing)
    • Consumer search engines, market monitors, product/service recommender systems
    • Client-supplier interaction platforms (e.g., portals, helps desks, newsgroups) and transaction support systems based on written or spoken natural language communication
    • Multi-media and multi-modality interaction platforms, including written/spoken language channels, supporting economic processes
    • Specialized modes of information extraction and text mining in economic domains, e.g., temporal event or transaction mining
    • Information aggregation from single sources (e.g., review summaries, automatic threading)
    • Text generation in economic domains, e.g., review generation, complaint response generation
    • Ontologies for economics and adaptation of general-domain lexicons for economic NLP
    • Corpora and annotations policies (guidelines, metadata schemata, etc.) for economic NLP
    • Economy-specific text genres (business reports, sustainability reports, auditing documents, product reviews, economic newswire, business letters, law documents, etc.) and their usage for NLP
    • Dedicated software resources for economic NLP (e.g., NER taggers, sublanguage parsers, pipelines for processing economic discourse)

Program Committee

  • Sven Büchel Friedrich-Schiller-Universität Jena, Jena, Germany
  • Hsin-Hsi Chen National Taiwan University, Taipei City, Taiwan
  • Paulo Cortez University of Minho, Guimarães, Portugal
  • Sanjiv Ranjan Das Santa Clara University, Santa Clara, CA, USA
  • Brian Davis Maynooth University, Maynooth, Ireland
  • Flavius Frasincar Erasmus University, Rotterdam, Netherlands
  • Petr Hájek University of Pardubice, Pardubice, Czech Republic
  • Allan Hanbury Technische Universität Wien, Wien, Austria
  • Qing Li Southwestern University of Finance and Economics, Sichuan, Chengdu, China
  • Pekka Malo Aalto University, Aalto , Finland
  • Julian J. McAuley University of California at San Diego, San Diego, CA, USA
  • Viktor Pekar Aston University, Birmingham, UK
  • Paul Rayson Lancaster University, Lancaster, UK
  • Samuel Rönnqvist University of Turku, Turku, Finland
  • Sameena Shah S&P Global Ratings, New York City, NY, USA
  • Kiyoaki Shirai Japan Advanced Institute of Science and Technology (JAIST), Nomi, Japan
  • Padmini Srinivasan University of Iowa, Iowa City, IA, USA
  • Amanda Stent Bloomberg LP, New York City, NY, USA
  • Heiner Stuckenschmidt Universität Mannheim, Mannheim, Germany
  • Chuan-Ju Wang Academia Sinica, Taipei City, Taiwan
  • Wlodek W. Zadrozny University of North Carolina at Charlotte, Charlotte, NC, USA
  • Ming Zhou Microsoft Asia Research, Beijing, China

Final Program

9:00am – 10:40am Session 1: INTRO & FINANCIAL EVENT EXTRACTION

9:00am – 9:30am Introduction to the Workshop (Udo Hahn)

9:30am – 10:00am Extracting Complex Relations from Banking Documents (5-L)

Berke Oral, Erdem Emekligil, Seçil Arslan and Gülşen Eryiğit

10:00am – 10:20am Financial Event Extraction Using Wikipedia-Based Weak Supervision (93-S)

Liat Ein-Dor, Ariel Gera, Orith Toledo-Ronen, Alon Halfon, Benjamin Sznajder, Lena Dankin, Yonatan Bilu, Yoav Katz and Noam Slonim

10:20am – 10:40am A Time Series Analysis of Emotional Loading in Central Bank Statements (97-S)

Sven Buechel, Simon Junker, Thore Schlaak, Claus Michelsen and Udo Hahn

10:40 am – 11:00am Coffee break 1

11:00am – 12:30am Session 2: FINANCIAL FORECASTING & PREDICTION

11:00am – 11:30am Forecasting Firm Material Events from 8-K Reports (100-L)

Shuang (Sophie) Zhai and Zhu (Drew) Zhang

11:30am – 12:00am Incorporating Fine-grained Events in Stock Movement Prediction (7-L)

Deli Chen, Yanyan Zou, Xuancheng Ren, Ruihan Bao, Keiko Harimoto and Xu Sun

12:00am – 12:30am Group, Extract and Aggregate: Summarizing a Large Amount of Finance News for Forex Movement Prediction (6-L)

Deli Chen, Shuming Ma, Yanyan Zou, Keiko Harimoto, Ruihan Bao, Qi Su and Xu Sun

12:30am-2:00pm Lunch break

2:00pm – 3:30pm Session 3: Invited Talk. Miscellaneous Topics

2:00pm – 2:45pm Invited Talk: NLP for Financial Regulation

Marco Enriquez (Division of Economic and Risk Analysis, U.S. Securities and Exchange Commission)

2:45pm – 3:15pm Complaint Analysis and Classification for Economic and Food Safety (99-L)

João Filgueiras, Luís Barbosa, Gil Rocha, Henrique Lopes Cardoso, Luís Paulo Reis, João Pedro Machado, and Ana Maria Oliveira

3:15pm – 3:35pm Annotation Process for the Dialog Act Classification of a Taglish E-commerce Q&A Corpus (96-S)

Jared Rivera, Jan Caleb Oliver Pensica, Jolene Valenzuela, Alfonso Secuya and Charibeth Cheng

3:35pm – 4:00pm Coffee break 2

4:00 pm – 4:20pm Feedback round from the audience – future directions of ECONLP

4:20 pm – 6:00pm Poster presentations of all papers presented at the workshop

6:00pm end of the work