Handbook of logic in artificial intelligence and logic programming (vol. 3)
Machine Learning
Email overload: exploring personal information management of email
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
A vector space model for automatic indexing
Communications of the ACM
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
The description logic handbook: theory, implementation, and applications
The description logic handbook: theory, implementation, and applications
On the algorithmic implementation of multiclass kernel-based vector machines
The Journal of Machine Learning Research
Communities of action: a cognitive and social approach to the design of CSCW systems
GROUP '03 Proceedings of the 2003 international ACM SIGGROUP conference on Supporting group work
Ontology-Driven Affective Chinese Text Analysis and Evaluation Method
ACII '07 Proceedings of the 2nd international conference on Affective Computing and Intelligent Interaction
Communication-Garden System: Visualizing a computer-mediated communication process
Decision Support Systems
Ontological reasoning to configure emotional voice synthesis
RR'07 Proceedings of the 1st international conference on Web reasoning and rule systems
HCI'07 Proceedings of the 12th international conference on Human-computer interaction: intelligent multimodal interaction environments
Annotation of emotions and feelings in texts
ACII'05 Proceedings of the First international conference on Affective Computing and Intelligent Interaction
| Hi-index | 0.00 |
In Computer Supported Cooperative Work (CSCW), it is crucial for project leaders to detect conflicting situations as early as possible. Generally, this task is performed manually by studying a set of documents exchanged between team members. In this paper, we propose a full-fledged automatic solution that identifies documents, subjects and actors involved in relational conflicts. Our approach detects conflicts in emails, probably the most popular type of documents in CSCW, but the methods used can handle other text-based documents. These methods rely on the combination of statistical and ontological operations. The proposed solution is decomposed in several steps: (i) we enrich a simple negative emotion ontology with terms occuring in the corpus of emails, (ii) we categorize each conflicting email according to the concepts of this ontology and (iii) we identify emails, subjects and team members involved in conflicting emails using possibilistic description logic and a set of proposed measures. Each of these steps are evaluated and validated on concrete examples. Moreover, this approach's framework is generic and can be easily adapted to domains other than conflicts, e.g. security issues, and extended with operations making use of our proposed set of measures.