Call for papers
Scope
Our hyper-connected digital world is defined by an overabundance of data. From social media to news articles to machine logs, text data is everywhere. The growth in the volume of data created in different formats – text, image or video – and the speed with which they are generated provide interesting new research opportunities that explore social interactions, literature, languages, art, etc. Thinking about the Digital Humanities, at a time when we are witnessing this exponential increase in the volume of digital information available in different languages, inevitably leads us to the exploration of different branches associated with the area of Natural Language Processing (such as information extraction and retrieval, machine translation, automatic analysis of textual content, text summarization, text simplification, text generation, speech recognition and synthesis, among others).
For mining information from very large repositories of text, we need to know what we are looking for and how to analyse it. Our conference is a forum to exchange methods and practical applications 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 multimodal communication.
Topics
We invite linguistic experts, data scientists, IT professionals, developers, and anyone with a keen interest in generating insights from textual data to share ideas and advances on how open sources paradigm and new emerging research text analysis/analytics methods are applied to different fields of humanities and social sciences as well as to discuss current and future challenges. In particular, we encourage the submission of abstracts discussing challenges related to the main stages of data journey presented below. Topics include the following but are open for additional:
Getting text
data
Where and how do digital humanists find and clean their text data?
Open Access and Open Science
Digital libraries
Data repositories
Language Corpora
Social media
Audio/video data
Web scraping techniques
Text cleaning and parsing techniques
Tools for extracting and cleaning text data
Privacy and/or security requirements
Finding inspiration in text data
How do digital humanists find inspiration in their text data?
Document classification
Corpora comparison
Entity recognition
Summarization
Terminology extraction
Text statistics
Sentiment analysis & Opinion mining
Author profiling
New research methodologies and design
Text simplification
Telling a story with text data
Why do digital humanists need to tell stories with their text data?
Visualization as text simplification
Text adaptation
Infographics
Animated videos
Geolocalization
Interactive Dashboards
Instructional Design Research
Submission guidelines
Abstracts must be written in English, Times New Roman, size 12; justified. Abstracts should include: Title, 300 to 500 word summary, 3-5 key-words, 5 references (maximum). Abstracts will be refereed through double-blind peer review.
Submit your abstract at the following link: https://easychair.org/conferences/?conf=ddhum2023
In-person participants
In-person presentations are allocated 15 minutes, including Q&A. We suggest that the presentation of your slides takes about 10 minutes, leaving 5 minutes for an introduction by the session chair and questions from the audience.
Please upload your presentation file to the computer in the session room before the session starts. Note that the presentation computer has only USB ports.
Virtual participants
Virtual presentations are scheduled in virtual rooms. Virtual presentations are allocated 15 minutes (10 min presentation + 5 min Q&A). Access to the virtual rooms (in Zoom) will be provided by March 05.