Supporting efficient and reliable content analysis using automatic text processing technology

Authors:
Gahgene Gweon;Carolyn Penstein Rosé;Joerg Wittwer;Matthias Nueckles
Affiliations:
Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA;Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA;Institut Fuer Psychologie, Universitaet Freiburg, Freiburg, Germany;Institut Fuer Psychologie, Universitaet Freiburg, Freiburg, Germany
Venue:
INTERACT'05 Proceedings of the 2005 IFIP TC13 international conference on Human-Computer Interaction
Year:
2005

Citing 2
Cited 2

A Comparative Study on Feature Selection in Text Categorization

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Supporting CSCL with automatic corpus analysis technology

CSCL '05 Proceedings of th 2005 conference on Computer support for collaborative learning: learning 2005: the next 10 years!

Estimating annotation cost for active learning in a multi-annotator environment

HLT '09 Proceedings of the NAACL HLT 2009 Workshop on Active Learning for Natural Language Processing
Towards a prototyping tool for behavior oriented authoring of conversational agents for educational applications

EdAppsNLP 05 Proceedings of the second workshop on Building Educational Applications Using NLP

Quantified Score

Hi-index	0.00

Visualization

Abstract

Text categorization technology can be used to streamline the process of content analysis of corpus data. However, while recent results for automatic corpus analysis show great promise, tools that are currently being used for HCI research and practice do not make use of it. Here, we empirically evaluate trade-offs between semi automatic and hand labeling of data in terms of speed, validity, and reliability of coding in order to assess the usefulness of incorporating this technology into HCI tools.