Y.Yang
21/12/2015 (M) - 4/1/2016 (M)
Data Analysis of "Challenging Questions" & Insights
Y.Yang
4/1/2016
Existing Zara Response Data
Common Derailing/Difficult Topics
Relevant
(Functional but out of scope)
Irrelevant
(Socially inappropriate, existential/predictive questions)
Negative
Neutral
Positive
Strategic mitigation responses
184 responses in total
65 >= State1
16 challenges
Oct - Dec 2015
Seeking reciprocity from Zara
16 unique ID responses, 124 responses in total to all 15Q Zara posed. Of the 30 challenging responses, ...
Stated verbal avoidance of topic
Implied avoidance of topic
Abusive Language
Seeking Clarification
Deliberate Challenge of Zara's ability
--Categorical data validation with Prof Ma (are these the only classification?)
-- intention classification (intensive classifier), "garbage"
Seeking reciprocity from Zara
Avoidance of topic
Bonding
Mutual trust
Psychological need of Users
Intuition: Humans needs cues to bond with robots the same way humans bond with each other
Context: Most of the responses are from Asian users
How reliable are these insights?
-- 16 challenges/180 responses is a small sample size
-- Lee, M.K. et. al. "Gracefully Mitigating Breakdowns in Robotic Services" (2010) : 457 respondents to survey
How might Zara respond to challenging questions/derailing topics in an empathetically graceful manner that enhances mutual trust and information reciprocity?
-- Based on the psychological need of the users
-- Ease into conversations
Discussion with Prof Ma
-- Do we need more response data?
-- If yes, what setting and what factors should we control?
-- Intuition: Need more data
Mutual Trust Assumption Validation
-- Psychology literature on mutual trust and bonding
-- A. Aron et. al. "The Experimental Generation of Interpersonal Closeness" (1997)
Paper Submission Deadline: 18 Sep 2016
Conference Date: 6-11 May 2017
Location: Denver, USA
*According to: http://www.sigchi.org/conferences
Feb 12 Paper Deadline