INVESTIGADORES
CHESÑEVAR Carlos Ivan
congresos y reuniones científicas
Título:
Modeling User's Sentiment in User Segmentations: An Argumentation Approach for User Centered Design
Autor/es:
MARÍA PAULA GONZÁLEZ; CARLOS IVÁN CHESÑEVAR; RAMÓN BRENA
Lugar:
Los Angeles
Reunión:
Conferencia; Intl. Conf. on Human Computer Interaction 2015 (HCI 2015); 2015
Institución organizadora:
HCI Committee
Resumen:
User segmentation is a practice of clustering a audience base
into mutually exclusive subsets of individuals that are similar in specic
ways. Nowadays user segmentation is crucial not only for the industry but
also for the eld of User Centered Design, where achieving and accurate
understanding of user's behavior in the current e-scenario is becoming a
complex task. The segmentation could be based on demographic issues,
social-economical features, psychographic data, physical characteristics
and psychological proles, etc. This paper proposes a novel strategy for
the automatic detection of critical segmentation factors that divide users
focused on their feelings and opinions towards a particular topic. Given
a topic and on the basis of user's text-based opinions posted at web
2.0 services as social networks, microblogging platforms, online review
systems, online news media, etc.; our proposal introduces an argument
oriented methodology that integrates argumentation theory, sentiment
analysis and opinion mining including the computational treatment of
incomplete, contradictory or potentially inconsistent information. The
mining process is characterized in terms of dialectical analysis of opinions
(atomic or more complex opinions constructed by aggregation mechanism)
according to a preference criterion given by topic and feature
specicity. As a result, an \opinion analysis tree" rotted in the rst
original topic is automatically constructed and visualized, on which any
node models a user segmentation, showing the factor that dene the
segmentation as well as the particularities that group the subset. This
way, traditional problems associated with the subjective interpretation
of user's opinions expressed in natural language are minimized. Besides,
instead of dening a user's statistical sample, all available information is
considered and possible not evident critical segmentation factors could
be discovered, thus enhancing a rational decision making process.