PoliticalNLP 2024

Workshop Description

The use of large amounts of structured and unstructured text data in social and political sciences research has become increasingly prevalent. Consequently, there has been a significant growth in the development of text processing methods aimed at predicting, learning, and uncovering new insights from socio-political text data that is extensive and diverse.

This workshop will delve into the various aspects of effective Natural Language Processing techniques for socio-political data. Its objective is to establish a research platform dedicated to exploring novel methods and techniques for processing socio-political content and investigating their application in information extraction and analysis.

Launched in 2022 in conjunction with the LREC 2022 conference, this workshop continues to evolve as a platform for fostering collaborative research and exploration. 

This year's workshop will focus on the theme "Opportunities and Challenges of Generative AI and LLMs in Social and Political Sciences Research." However, contributions on any topic related to the theme are welcome, including but not limited to:

•   Migration flows, disaster or disease prediction, and forecasting

•   Modelling global events or human activities based on text analysis

•   Identification and geo-location of social media content

•   Social-based web platform for disaster management

•   Resource allocation using social media

•   Monitoring emergency responses among social crowds

•   Analysing the diffusion of emergent information

•   Exploiting text generation for crisis response and rescue activities

•   Ethical concerns and ethical design of NLP applications in socio-political sciences

The PoliticalNLP workshop aims to provide a platform for discussing the implementation of language technologies in the field of social and political sciences. Computational social and political scientists will be invited to present and discuss their NLP tools, comparing them to traditional coding approaches. Computational linguistics and machine learning practitioners and researchers will benefit from engaging with real-world use cases in these domains.

Contributions to the workshop can take the form of:

-        Regular long papers – up to eight (8) pages maximum, presenting substantial, original, completed, and unpublished work.

-        Short papers – up to four (4) pages, describing a small focused contribution, negative results, system demonstrations, etc.

-        Position papers – up to eight (8) pages, discussing key hot topics, challenges and open issues, as well as cross-fertilization between NLP, Social Science, and other disciplines.

(*) Excluding any number of additional pages for references, ethical consideration, conflict-of-interest, as well as data and code availability statements.

In line with the WiNLP initiative, we recognize and address the demographic imbalance within computational linguistics. To champion diversity and inclusivity, we actively encourage submissions from under-represented groups. Embracing diverse perspectives enriches our discourse and strengthens our collective pursuit of knowledge in this field.

Identify, Describe and Share your LRs!

• Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). To continue the efforts initiated at LREC 2014 about “Sharing LRs” (data, tools, web-services, etc.), authors will have the possibility,  when submitting a paper, to upload LRs in a special LREC repository.  This effort of sharing LRs, linked to the LRE Map for their description, may become a new “regular” feature for conferences in our field, thus contributing to creating a common repository where everyone can deposit and share data.

• As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, LREC-COLING 2024 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.

Important Dates

• Paper Submission deadline (short and long papers): March 5th, 2024, March 12th, 2024, 23:59 UTC+1

• Notification of acceptance: March 20th, 2024, 23:59 UTC+1

• Camera-ready papers due: March 28th, 2024, 23:59 UTC+1

• Early registration deadline: April 15th, 2024

• PoliticalNLP Workshop: May 21st, 2024 (Full Day).

Paper Submission Instructions

Submission URL: https://softconf.com/lrec-coling2024/politicalnlp2024/

Types of Papers: We invite long and short research papers. Long paper submissions are expected to describe substantial, original, completed, and unpublished work. Characteristics of short papers include a small, focused contribution; a work in progress; a negative result; an opinion piece; or an interesting application nugget. 

Paper Length: As per  LREC-COLING 2024 policy, Long research papers may consist of up to 8 pages of content, plus unlimited references and appendices; final versions of long papers will be given one additional page of content (up to 9 pages) so that reviewers’ comments can be taken into account. Short research papers may consist of up to 4 pages of content, plus unlimited references; final versions of short papers will be given one additional page of content (up to 5 pages) so that reviewers’ comments can be considered.

Submission Formatting: Please follow the LREC official LaTeX or Word templates available at LREC-COLING 2024 Author's kit and paper formatting guidelines

Blind Reviewing Policy: The workshop follows a blind reviewing policy. The authors should omit their names and affiliations from the paper and avoid self-references that reveal their identities. Papers that do not conform to these requirements will be rejected without review. Accepted papers will be published in the workshop proceedings.

Double submission policy: Parallel submission to other meetings or publications is possible but must be immediately notified to the workshop organizers.

For further information, please contact Haithem Afli (Haithem.Afli@mtu.ie)

Workshop Organizers                                       

General Chair: Haithem Afli, ADAPT Centre, Munster Technological University, Ireland

Program Chairs: 

• Houda Bouamor, Carnegie Mellon University, Qatar

• Sahar Ghannay, Université Paris-Saclay, CNRS, LISN, France

• Cristina Blasi Casagran, Autonomous University of Barcelona, Spain

Program Committee

• Wajdi Zaghouani, Hamad Bin Khalifa University, Qatar

• Bruno Andrade, Munster Technological University, Ireland

• Lenka Dražanová, European University Institute, Italy

• Georgios Stavropoulos, The Centre for Research and Technology, Greece

• Andrea Iana, University of Mannheim, Germany

• Valentin Barrieren, Telecom ParisTech, France

• Mohammed Hasanuzzaman, Munster Technological University, Ireland

• Patrick Paroubek, Paris-Saclay University, CNRS, LISN, France

• Suman Adhya, Indian Association for the Cultivation of Science, India

• Valentin Barriere, Centro Nacional de Inteligencia Artificial, Santiago, Chile

Program PoliticalNLP @ LREC-COLING 2024 (Full day workshop) 

Tuesday, May 21st , 2024 - Lingotto Conference Centre - Torino (Italia)

09:00–09:10 Opening and Welcome by Haithem Afli

09:10–09:40   Some Unchained Thoughts on Language, Computer, and Politics

                       Keynote Speech by Patrick Paroubek

09:40–10:45 Oral session 1: Political News and Sentiment 

09:40–10:05    Multi-Dimensional Insights: Annotated Dataset of Stance, Sentiment, and Emotion in Facebook Comments 

                        on Tunisia’s July 25   Measures

                       Sanaa Laabar and Wajdi Zaghouani

10:05–10:30   Deciphering Political Entity Sentiment in News with Large Language Models: Zero-Shot and Few-Shot Strategies

                       Alapan Kuila and Sudeshna Sarkar

10:30–11:00 Morning Coffee Break

11:00–13:00 Oral session 2: Political User-Generated Content 

11:00–11:25 Masking Explicit Pro-Con Expressions for Development of a Stance Classification Dataset on Assembly Minutes

                          Tomoyosi Akiba, Yuki Gato, Yasutomo Kimura, Yuzu Uchida and Keiichi Takamaru

11:25–11:50 Analysing Pathos in User-Generated Argumentative Text

                  Natalia Evgrafova, Veronique Hoste and Els Lefever

11:50–12:15 Echo-chambers and Idea Labs: Communication Styles on Twitter

                      Aleksandra Sorokovikova, Michael Becker and Ivan P. Yamshchikov

12:15–12:45 Knowledge Graph Representation for Political Information Sources

                   Tinatin Osmonova, Alexey Tikhonov and Ivan P. Yamshchikov

13:00–14:00 Lunch Break

14:00–14:45     GenAI and LLMs: Shaping Social and Political Sciences

                          Panel discussion featuring Stephanie Brand, Cristina Blasi Casagran, and Sahar Ghanney 

                          with moderation by Haithem Afli.

14:45–16:45 Oral session 3: Political Events and Reports 

14:45–15:10 Event Detection in the Socio Political Domain

                      Emmanuel CARTIER and Hristo Tanev

15:10–15:35 Analyzing Conflict Through Data: A Dataset on the Digital Framing of Sheikh Jarrah Evictions 

                      Anatolii Shestakov and Wajdi Zaghouani 

15:35–16:00 Semi-Automatic Topic Discovery and Classification for Epidemic Intelligence via Large Language Models                    

                      Federico Borazio, Danilo Croce, Giorgio Gambosi, Roberto Basili,Daniele Margiotta, Antonio Scaiella, Martina Del Manso, 

                        Daniele Petrone, Andrea Cannone, Alberto M. Urdiales, Chiara Sacco, Patrizio Pezzotti, Flavia Ric- cardo, 

                        Daniele Mipatrini, Federica Ferraro and Sobha Pilati

16:00–16:30 Afternoon Coffee Break

16:30–16:55 Towards quantifying politicization in foreign aid project reports

                      Sidi Wang, Gustav Eggers, Alexia de Roode Torres Georgiadis,Tuan Anh Ðo, Léa Gontard, Ruth Carlitz and Jelke Bloem

16:55–17:00 Closing remarks by Haithem Afli