![](bg7.png)
6 CONCLUSIONS
The objective of our research is to discover problem-
solving knowledge from computer mediated
communication within a professional project. In this
paper, we present a method using business emails
for this aim. Email was considered as a specific
asynchronous and not face to face kind of discourse
and we applied some pragmatics analysis to it.
Speech act analysis alone is a difficult problem, so
we consider it inside the project context: human
organization and skills, and project specifications.
Our questions were: Does emails contain any useful
trace of project related knowledge? And could we
identify an appropriate method to extract and
structure it?
The principle of our approach is to take into
account all the aspects of the mediated exchanges
during a project. Thus we have presented a general
guideline to detect interesting (related to problem
solving in software design) threads among a vast
amount of messages. We then have proposed a
custom coding scheme to detect request and clarify
ambiguity in sentence analysis. To illustrate this, we
have analyzed a professional project corpus and
detect some parts of problems and possible answers.
On the whole these results confirm the applicability
of the technique, and we will further investigate on
different types of project and other grid of analysis
like: decision making, negotiations, and design
rationale (Matta et al, 2011). It comfort us that when
emails is not only seen as way to broadcast
information, but as a media allowing online
exchanges, like discourses, it could turn into a
source of knowledge.
Our current work objective is to explore various
techniques from machine learning to implement
support algorithm for the projection of our features
vectors (topics, pragmatics and context) to problem-
solving knowledge model. Although related to the
works of Cleland-Huang (Cleland-Huang et al,
2006) on Requirement traceability in software
design, we will focused more on functional testing
and design detection. Finally, this study is a part of
our work on project memory: traceability and
structuration of knowledge in daily work realization
of project.
REFERENCES
Baron, N. S., 1998. Letters by phone or speech by other
means: The linguistics of email. In Language &
Communication, 18(2), p133-170.
Beck, K., Beedle, M., Van Bennekum, A., Cockburn, A.,
Cunningham, W., Fowler, M., Thomas, D., 2001.
Manifesto for agile software development.
Bekhti, S., Matta, N., 2003. Project memory: an approach
of modelling and reusing the context and the de design
rationale.In Proceedings of IJCAI’03 (International
Joint of Conferences of Artificial Intelligence),
Workshop on Knowledge Management and
Organisational Memory, Acapulco.
Benveniste E., 1966. Problèmes de linguistique générale,
t. I, Paris, Gallimard.
Carvalho, V., Cohen, W., 2004. Learning to extract
signature and reply lines from email. In Proceedings
of the Conference on Email and Anti-Spam, Palo Alto,
CA.
Carvalho, V.R., Cohen, W., 2006. Improving "email
speech acts" analysis via n-gram selection. In
Proceedings of the HLT-NAACL 2006 Workshop on
Analyzing Conversations in Text and Speech (ACTS
'09). Association for Computational Linguistics,
Stroudsburg, PA, USA, p35-41.
Cleland-Huang, J.; Settimi, R.; Xuchang Zou; Solc, P.,
2006. The Detection and Classification of Non-
Functional Requirements with Application to Early
Aspects. In Requirements Engineering, 14th IEEE
International Conference, p39-48.
Cselle, G., Albrecht, K., Wattenhofer, R., 2007.
BuzzTrack: topic detection and tracking in email.
In Proceedings of the 12th international conference on
Intelligent user interfaces, p190-197.
De Felice, R., Deane, P., 2012. Identifying speech acts in
emails: Toward automated scoring of the TOEIC®
email task. In ETS Research Report No. RR-12-16,
Princeton.
Diesner, J., 2005. Exploration of Communication
Networks from the Enron Email Corpus. In
Proceedings of Workshop on Link Analysis,
Counterterrorism and Security, SIAM International
Conference on Data Mining 2005, p3-14.
Gray, P. H., 2001. A problem-solving perspective on
knowledge management practice. In Decision Support
System 31, 1 (May 2001), p87-102.
Goffman, E., 1956. The Presentation of Self in Everyday
Life, University of Edinburgh Social Sciences
Research Centre Monographs, no2.
Gospodnetic, O., Hatcher, E., 2004. Lucene in Action.
Manning Publications.
Hardin, L. E. 2002. Problem Solving Concepts and
Theories. In Journal of Veterinary Medical Education,
30(3), p227-230.
Herring, S. C., 2004. An Approach to Researching Online
Behavior. Designing for virtual communities in the
service of learning. In S. A. Barab, R. Kling, J. H.
Gray (Eds.), designing for Virtual Communities in the
KMIS2014-InternationalConferenceonKnowledgeManagementandInformationSharing
192