We introduce the particular functionality of the Co mplaint Engine suite, the integrated complaint management component for mediating consumer disputes. We formulate the problem of epistemic categorization: whether a given complaint submitted by an upset customer is an adequate representation of company’s product, servi ce and attitude towards customers. To do that, a sequence of communicative actions and argumentation patterns in the course of complaint resolution (as described by a complainant) is analyzed. Instead of natural la nguage processing of textual complaints we use two interac tive forms: the first one, to specify communicative acti ons and argumentative links between their parameters, and t he second one, to specify the argumentative relations between the major claims. We briefly outline the reasoning components involved in processing the above data to extract information which would then be expected to be truthful. We then perform the comparative evaluatio n of the involved reasoning units.
[1]
Bernhard Ganter,et al.
Pattern Structures and Their Projections
,
2001,
ICCS.
[2]
Guillermo Ricardo Simari,et al.
Defeasible logic programming: an argumentative approach
,
2003,
Theory and Practice of Logic Programming.
[3]
Ana Gabriela Maguitman,et al.
Logical models of argument
,
2000,
CSUR.
[4]
Patrick Brézillon,et al.
Lecture Notes in Artificial Intelligence
,
1999
.
[5]
Boris A. Galitsky,et al.
Justification of Customer Complaints using Emotional States and Mental Actions
,
2004,
FLAIRS.
[6]
Boris A. Galitsky,et al.
Analyzing Conflicts with Concept-Based Learning
,
2005,
ICCS.
[7]
Boris A. Galitsky.
Merging deductive and inductive reasoning for processing textual descriptions of inter-human conflicts
,
2006,
Journal of Intelligent Information Systems.
[8]
K. Bach,et al.
Linguistic Communication and Speech Acts
,
1983
.