1st International Conference on Data & Digital Humanities 

Text Mining and Multimodal Storytelling



08 – 10 March, 2023 · University of Minho, Braga, Portugal (hybrid conference)

We are pleased to announce the 1st International Conference Data & Digital Humanities, which will take place at the University of Minho, Braga, Portugal, on 08-10 March 2023, as a virtual and face-to-face conference. This will be an event hosted by CEHUM – Center for Humanistic Studies. This congress is part of the research project PortLinguE (PTDC/LLT-LIG/31113/2017), entitled "Multilingual portal for specialized languages: mining open data for cross-language information retrieval", in collaboration with the research project DIAL4U (2020-1-FR01-KA226-HE-095526), entitled "Digital pedagogy to develop Autonomy, mediate and certify Lifewide and Lifelong Language Learning for (European) Universities" and with the research project SimpleText (University of Bretagne Occidentale). This conference arises from the dialogue between these funded projects and the desire to share the research results and bring new practices for text mining, open data and open science to the academic community.

The conference covers the three main steps for processing textual data in multilingual environments and aims to make data science methods more accessible to the larger community and to the Humanities in particular:

Getting and cleaning all your text data before analyzing it


Exploring your data using different methods and tools


Presenting your data in a clear and compelling way 

The idea is to be able to gather, clean, manipulate, and analyze textual data as well as to weave it into compelling, action-inspiring stories using different and new digital forms of representation/communication. 


Read more: Call for Papers

A Conference for all text data lovers to come together to share, inspire, and innovate.

 Keynote speakers

To access the keynotes sessions use the following zoom link: 

See the program for schedules:

To change or to transform higher education: can this be the question?

Data Science and  Humanities

Research and Open Science

Manuel João

(University of Minho)

Associate Professor at the School of Medicine (previously designated School of Health Sciences) since 2011.


Degree in Biochemistry from the University of Porto in 1991.

Doctor in Biomedical Sciences from the same University in 1997.

He joined the University of Minho as Assistant Professor in 2004.

He was a member of the General Council of the University of Minho between 2017 and 2018.


He develops his teaching activity in the areas of biochemistry and molecular biology and in education in the health sciences.

He does research in teaching and learning in higher education, with a focus on medical education and the biomolecular sciences. 


At the School of Medicine, he served as coordinator of the medical education unit. He was president of the committee to access to the medical degree by graduate between the academic years 2013/14 and 2017/2018. During the same period, he was responsible for the medical school's teacher development program. At the University of Minho, he participated in the founding of the Center IDEA-UMinho.

(Data Science Portuguese Association)

Graduated in Management, he accumulates a vast national and international experience, academic and professional, in the development and management of projects in different areas and sectors of activity, with emphasis on technology-based services, having in recent years performed the functions of Secretary General of Portugal Outsourcing Association and Director of International Business Development for companies belonging to a Portuguese group in the areas of Technological and Innovation Consulting and Outsourcing Services. Executive Director of the DSPA - Data Science Portuguese Association since its foundation in 2018, he is enthusiastic about the processes of creating projects from scratch, developing, training and enhancing them based on personal and transversal professional skills.

(University of Minho)

Eloy Rodrigues is the Director of the University of Minho Libraries. Eloy has been working on repositories, Open Access and Open Science for almost two decades, having established University of Minho institutional repository in 2003, and coordinating the UMinho team which works on RCAAP (Portugal Open Access Science Repositories) since 2008. At international level he has being working on several EU funded projects (like OpenAIRE and FOSTER) related with Open Access and Open Science and is member of the European University Association Expert Group on Science 2.0/Open Science. Eloy was the Chair of the Executive Board of COAR, the Confederation of Open Access Repositories from 2015 to 2021, and in that role contributed actively to Next Generation Repositories initiative, the Pubfair conceptual model and the ongoing Notify Project, in which he is one of the Principal Investigators. Eloy is currently member of the Executive Board of OpenAIRE and of the Advisory Committee of SciELO Portugal.


 Narrative Extraction from Texts: an NLP approach

YAKE! Extracting Keywords from Text Documents

Experiments in distant reading in Portuguese

Alípio Jorge

(U. Porto / INESC TEC)

Alipio Jorge works in machine learning, recommender systems and NLP. He is a graduate in Applied Mathematics / Computer Science by UP, a PhD in Computer Science, also by UP, and MSc by the Imperial College. He is Associate Professor of the Department of Computer Science of the University of Porto since 2009 and is the head of that department since 2017. Alípio coordinates LIAAD, a unit of INESC TEC. He has projects in narrative extraction, web automation, recommender systems, information retrieval and decision support. He mostly lectures Data Science, Machine Learning and Programming. He coordinated and helped to launch master courses on Data Analytics and Data Science as well as the Bsc on Artificial Intelligence and Data Science. He was  Portugal's representative for Artificial Intelligence at the European Commission from 2018 to 2021.

(Polytechnic Institute of Tomar (IPT) 

Ricardo Campos is an Assistant Professor at the Polytechnic Institute of Tomar (IPT) and lecturer at the Porto Business School (PBS). He is a senior researcher of LIAAD-INESC TEC, the Artificial Intelligence and Decision Support Lab of U. Porto, and a collaborator of Ci2.ipt, the Smart Cities Research Center of the Polytechnic of Tomar.

 

He is PhD in Computer Science from the University of Porto (U. Porto), being also a former student of the University of Beira Interior (UBI). He has more than 10 years of experience in Information Retrieval (IR) and Natural Language Processing (NLP), period during which his research has been recognized with multiple awards.

 

He is the leading author of the highly impactful Yake! keyword extractor toolkit (http://yake.inesctec.pt) and the tell me stories project (http://contamehistorias.pt). His current research focuses on developing methods concerned with the process of narrative extraction from texts. He is particularly interested in practical approaches regarding the relationship behind entities, events, and temporal aspects, as a means to make sense of unstructured data. Currently, he is a co-pi of two research projects.

 

He is an editorial board member of the Information Processing & Management Journal (Elsevier), co-chaired international conferences and workshops, and is a regular member of the scientific committee of several international conferences. 

 

He is also a member of the Scientific Advisory Forum of the Portulan Clarin - Research Infrastructure for the Science and Technology of Language (https://portulanclarin.net) which is part of CLARIN ERIC (https://www.clarin.eu/).

 

More in http://www.ccc.ipt.pt/~ricardo

Diana Santos

(University of Oslo) 

Diana Santos has worked in natural language processing (NLP) of Portuguese for many decades, after graduating, defending her MSc thesis and PhD all from Instituto Superior Técnico, Lisbon, in 1985, 1988 and 1996, respectively. She has been the leader of Linguateca -- a resource and evaluation network for the processing of Portuguese -- since 1998, in which scope she has worked on corpora, semantics and evaluation. She is currently professor of Portuguese linguistics at the University of Oslo, and has been working with distant reading for the past years.

See the program for schedules:

Workshops

To access the workshops use the following zoom link: 

See the program for schedules:

Large pre-trained models for scientific text analysis

Liana Ermakova 

(University of Bretagne Occidentale) 

Exploring generative AI tools: Can ChatGPT be used as a personalized learning assistant?

Laboratório de Humanidades Digitais

(University of Minho)

Design for Information: Network Analysis and Introduction to Gephi.

Bruno Azevedo

(University of Minho) 

Textos históricos em Humanidades Digitais: dados ligados, ferramentas e recursos

(Universidade Federal Rio Grande Sul)

Panel Discussion

To access the Panels Discussion use the following zoom link: 

See the program for schedules:

DH Teaching Resource Development  - Present and Future


Sree Ganesh Thotempudi 

Application of Automatic Word Sense Disambiguation to Topic Modeling Solutions

We look forward to welcoming you all to an enriching conference with open discussions and important networking to promote the humanities and social sciences in the digital age.

Escola de Letras, Artes e Ciências Humanas
Université de Bretagne Occidentale
CEHUM
Project DIAL4U
Fundação para Ciência e a Tecnologia