Influence of Content Layout and Motivation on Users' Herd Behavior in Social
Discovery
Supporting Information Seeking
/
Yue, Yanzhen
/
Ma, Xiaojuan
/
Jiang, Zhenhui
Proceedings of the ACM CHI'16 Conference on Human Factors in Computing
Systems
2016-05-07
v.1
p.5715-5719
© Copyright 2016 ACM
Summary: Social product discovery is an emerging paradigm that enables users to seek
information and inspiration from peer-contributed contents. Researchers have
observed herd behaviors in social discovery, i.e., basing beliefs and decisions
on what similarly situated others have done. In this paper, we explore the
effects of content layout and motivation on users' herd behaviors in social
discovery. We conduct an eye-tracking study with 120 participants to compare
goal- and action-oriented users' behaviors on a grid versus waterfall style
social discovery site. The results show that users have a higher tendency to
herd on a grid-style website, more so for goal-oriented users.
Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval
Information Retrieval and Search
/
Sha, Long
/
Lucey, Patrick
/
Yue, Yisong
/
Carr, Peter
/
Rohlf, Charlie
/
Matthews, Iain
Proceedings of the 2016 International Conference on Intelligent User
Interfaces
2016-03-07
v.1
p.336-347
© Copyright 2016 ACM
Summary: The recent explosion of sports tracking data has dramatically increased the
interest in effective data processing and access of sports plays (i.e., short
trajectory sequences of players and the ball). And while there exist systems
that offer improved categorizations of sports plays (e.g., into relatively
coarse clusters), to the best of our knowledge there does not exist any
retrieval system that can effectively search for the most relevant plays given
a specific input query. One significant design challenge is how best to phrase
queries for multi-agent spatiotemporal trajectories such as sports plays. We
have developed a novel query paradigm and retrieval system, which we call
Chalkboarding, that allows the user to issue queries by drawing a play of
interest (similar to how coaches draw up plays). Our system utilizes effective
alignment, templating, and hashing techniques tailored to multi-agent
trajectories, and achieves accurate play retrieval at interactive speeds. We
showcase the efficacy of our approach in a user study, where we demonstrate
orders-of-magnitude improvements in search quality compared to baseline
systems.
Semantic Path based Personalized Recommendation on Weighted Heterogeneous
Information Networks
Session 2F: Heterogeneous Networks
/
Shi, Chuan
/
Zhang, Zhiqiang
/
Luo, Ping
/
Yu, Philip S.
/
Yue, Yading
/
Wu, Bin
Proceedings of the 2015 ACM Conference on Information and Knowledge
Management
2015-10-19
p.453-462
© Copyright 2015 ACM
Summary: Recently heterogeneous information network (HIN) analysis has attracted a
lot of attention, and many data mining tasks have been exploited on HIN. As an
important data mining task, recommender system includes a lot of object types
(e.g., users, movies, actors, and interest groups in movie recommendation) and
the rich relations among object types, which naturally constitute a HIN. The
comprehensive information integration and rich semantic information of HIN make
it promising to generate better recommendations. However, conventional HINs do
not consider the attribute values on links, and the widely used meta path in
HIN may fail to accurately capture semantic relations among objects, due to the
existence of rating scores (usually ranging from 1 to 5) between users and
items in recommender system. In this paper, we are the first to propose the
weighted HIN and weighted meta path concepts to subtly depict the path
semantics through distinguishing different link attribute values. Furthermore,
we propose a semantic path based personalized recommendation method SemRec to
predict the rating scores of users on items. Through setting meta paths, SemRec
not only flexibly integrates heterogeneous information but also obtains
prioritized and personalized weights representing user preferences on paths.
Experiments on two real datasets illustrate that SemRec achieves better
recommendation performance through flexibly integrating information with the
help of weighted meta paths.
Share your view: impact of co-navigation support and status composition in
collaborative online shopping
Social media usage
/
Yue, Yanzhen
/
Ma, Xiaojuan
/
Jiang, Zhenhui
Proceedings of ACM CHI 2014 Conference on Human Factors in Computing Systems
2014-04-26
v.1
p.3299-3308
© Copyright 2014 ACM
Summary: Collaborative online shopping, an emerging paradigm in e-commerce, allows
remote shoppers to extend purchase-oriented social interactions into the
digital environment. Online vendors have been experimenting ways to facilitate
this activity. However, more research needs to be done on identifying what
feature can create a pleasing shopping experience and ultimately encourage
spending. In this paper, we present an exploration of the impact of
co-navigation supports, including location cue, split screen, and shared view,
on the experiences and performance of 60 co-shopper dyads. We also studied if
status composition of shopping companions played a role in this process. By
analyzing about 1800 minutes of eye-tracking data, video footages, and web
logs, we found that split screen encouraged more diverse product search, shared
view enabled better coordination, and location cue was the least distracting.
Co-buyers achieved better factual and inference understanding, though
buyer-advisor dyads were more likely to stay together.
Personalized collaborative clustering
Collaborative recommendation systems
/
Yue, Yisong
/
Wang, Chong
/
El-Arini, Khalid
/
Guestrin, Carlos
Proceedings of the 2014 International Conference on the World Wide Web
2014-04-07
v.1
p.75-84
© Copyright 2014 ACM
Summary: We study the problem of learning personalized user models from rich user
interactions. In particular, we focus on learning from clustering feedback
(i.e., grouping recommended items into clusters), which enables users to
express similarity or redundancy between different items. We propose and study
a new machine learning problem for personalization, which we call collaborative
clustering. Analogous to collaborative filtering, in collaborative clustering
the goal is to leverage how existing users cluster or group items in order to
predict similarity models for other users' clustering tasks. We propose a
simple yet effective latent factor model to learn the variability of similarity
functions across a user population. We empirically evaluate our approach using
data collected from a clustering interface we developed for a goal-oriented
data exploration (or sensemaking) task: asking users to explore and organize
attractions in Paris. We evaluate using several realistic use cases, and show
that our approach learns more effective user models than conventional
clustering and metric learning approaches.
Atelier of smart garments and accessories
Workshop: atelier of smart garments and accessories
/
Caon, Maurizio
/
Yue, Yong
/
Andreoni, Giuseppe
/
Mugellini, Elena
Adjunct Proceedings of the 2013 International Joint Conference on Pervasive
and Ubiquitous Computing
2013-09-08
v.2
p.379-384
© Copyright 2013 ACM
Summary: Wearable computing represented an important paradigm shift in engineering
and computer science. At the present time, wearable computing is undergoing a
new paradigm shift: the wearable systems that used to be transportable devices
are actually weaving itself into "the fabric of everyday life" (as predicted by
Weiser). Indeed, the current trend of wearable computing is integrating the
technology directly in the garments without introducing new body-worn systems.
Clothes, shoes, eye-glasses, bracelets and watches are becoming smarter,
seamlessly embedding more and more powerful computational resources and
communication possibilities. The change has already begun and this workshop
aims to bring together researchers from the academia and the industry in order
to establish a multidisciplinary community interested in discovering and
exploring the challenges and opportunities coming from this natural evolution
of wearable computing.
Context-Aware Multimodal Sharing of Emotions
Adaptive, Personalised and Context-Aware Interaction
/
Caon, Maurizio
/
Angelini, Leonardo
/
Yue, Yong
/
Khaled, Omar Abou
/
Mugellini, Elena
HCI International 2013: 15th International Conference on HCI, Part V:
Towards Intelligent and Implicit Interaction
2013-07-21
v.5
p.19-28
Keywords: affective computing; multimodal interaction; computer mediated
communication; social sharing of emotions
© Copyright 2013 Springer-Verlag
Summary: Computer mediated interaction often lacks of expressivity, in particular for
emotion communication. Therefore, we present a concept for context-aware
multimodal sharing of emotions for human-to-computer-to-human interaction in
social networks. The multimodal inputs and outputs of this system are
distributed in a smart environment in order to grant a more immersive and
natural interaction experience. The context information is used to improve the
opportuneness and the quality of feedback. We implemented an evaluation
scenario and we conducted an observation study during some events with the
participants. We reported our considerations at the end of this paper.
The Effects of Navigation Support and Group Structure on Collaborative
Online Shopping
Society, Business and Health
/
Cheng, Yihong
/
Yue, Yanzhen
/
Jiang, Zhenhui (Jack)
/
Kim, Hyung Jin
OCSC 2013: 5th International Conference on Online Communities and Social
Computing
2013-07-21
p.250-259
Keywords: Collaborative Online Shopping; Navigation Support; Group Structure; Ease of
Uncoupling Resolution; Perceived Usefulness
© Copyright 2013 Springer-Verlag
Summary: As a new paradigm of e-commerce, collaborative online shopping fulfills
online consumers' needs to shop with close ones in a social and collaborative
environment. While previous e-commerce research and practice mainly focus on
consumers' individual shopping behavior, a recent trend is for consumers to buy
things together online. This study proposes two new types of navigation support
and investigates how different types of navigation support influence consumers'
collaborative online shopping experience. Specifically, their impacts on
consumers' coordination performance and perceived usefulness are assessed by
comparing two types of extant navigation support in a lab experiment.
Meanwhile, the moderating role of the group structure of collaborative
consumers is also assessed.
Kinesiologic electromyography for activity recognition
Signal and image processing for ambient intelligence and pervasive computing
/
Caon, Maurizio
/
Carrino, Francesco
/
Ridi, Antonio
/
Yue, Yong
/
Khaled, Omar Abou
/
Mugellini, Elena
Proceedings of the 2013 International Conference on PErvasive Technologies
Related to Assistive Environments
2013-05-29
p.34
© Copyright 2013 ACM
Summary: This paper presents a wearable system based on kinesiologic electromyography
that recognizes the user activity in real time. In particular, the system
recognizes the following five activities: "walking", "running", "cycling",
"sitting" and "standing". We conducted a study in order to select the opportune
muscles and sensors placement. Furthermore, we evaluated the system conducting
two analyses: impersonal and subjective. The impersonal analysis evaluated the
system behavior when it was trained on several users' data; on the opposite,
the subjective analysis evaluated the system when it was specialized on a
single subject data. In the impersonal analysis, the accuracy rate was 96.8%
for the 10-fold cross-validation and 91.8% for the leave one subject out. The
system accuracy rate for the subjective analysis was 99.4%.
Co-Navigability, Tracking Fulfillment and Autonomy in Collaborative Online
Shopping
/
Yue, Yanzhen
/
Jiang, Zhenhui
Proceedings of the 2012 AIS SIGHCI Workshop on HCI Research in MIS
2012-12-16
p.2
Keywords: online shopping, tracking fulfillment, collaborative shopping
Summary: Shopping is generally a social behavior, frequently done while accompanied
by friends or family. Lack of social interaction is considered to be a critical
barrier that defers customers from shopping online. As a new paradigm of
e-commerce, collaborative online shopping (COS), defined by Zhu et al. (2010)
as "the activity in which a customer shops at an online store concurrently with
one or more remotely located shopping partners", may dramatically improve
customers online shopping experience by fulfilling their needs to shop in a
social and collaborative way (O'Hara and Perry, 2001). Collaborative online
shopping would not only benefit online customers, but also furnish online
vendors with more potential revenues, since shoppers accompanied by others
generate more need recognition and spend more than when shopping alone (Kurt et
al., 2011). Collaborative online shopping is emerging as an instrumental way to
largely increase customer satisfaction and generate more revenues for online
vendors. For example, according to Internet Retailer (2010), collaborative
online shopping helps drive 15% increase in sales at a leading German skincare
website. Although collaborative online shopping is very common in everyday life
(Huang et al., 2012), it is not well supported by current systems (Benbasat,
2010). Due to the very few findings on COS, both the guidelines for system
designers and our understanding towards theCOSmechanisms are rather limited. To
fill this research gap, we argue that when customers collaboratively shop with
their companions online, they act both as individuals and as members of the
shopping group. As shopping group members, customers require information about
each other to maintain awareness; while as individuals, they demand flexible
means for interacting with the website and the product information (Gutwin and
Greenberg, 1998). In consideration of the paramount benefits for online
customers/vendors and the deficiency in research findings, much more effort is
desired for researchers to comprehensively explore how systems could be
designed to better support COS and improve collaborative online customers'
shopping experience by balancing both the group needs (e.g. share and discuss
information with each other) and the individual needs (e.g. freely browse
product information without much interruption from partners).
Large-scale validation and analysis of interleaved search evaluation
/
Chapelle, Olivier
/
Joachims, Thorsten
/
Radlinski, Filip
/
Yue, Yisong
ACM Transactions on Information Systems
2012-02
v.30
n.1
p.6
© Copyright 2012 ACM
Summary: Interleaving is an increasingly popular technique for evaluating information
retrieval systems based on implicit user feedback. While a number of isolated
studies have analyzed how this technique agrees with conventional offline
evaluation approaches and other online techniques, a complete picture of its
efficiency and effectiveness is still lacking. In this paper we extend and
combine the body of empirical evidence regarding interleaving, and provide a
comprehensive analysis of interleaving using data from two major commercial
search engines and a retrieval system for scientific literature. In particular,
we analyze the agreement of interleaving with manual relevance judgments and
observational implicit feedback measures, estimate the statistical efficiency
of interleaving, and explore the relative performance of different interleaving
variants. We also show how to learn improved credit-assignment functions for
clicks that further increase the sensitivity of interleaving.
Practical online retrieval evaluation
Tutorials
/
Radlinski, Filip
/
Yue, Yisong
Proceedings of the 34th Annual International ACM SIGIR Conference on
Research and Development in Information Retrieval
2011-07-25
p.1301-1302
© Copyright 2011 ACM
Summary: Online evaluation is amongst the few evaluation techniques available to the
information retrieval community that is guaranteed to reflect how users
actually respond to improvements developed by the community. Broadly speaking,
online evaluation refers to any evaluation of retrieval quality conducted while
observing user behavior in a natural context. However, it is rarely employed
outside of large commercial search engines due primarily to a perception that
it is impractical at small scales. The goal of this tutorial is to familiarize
information retrieval researchers with state-of-the-art techniques in
evaluating information retrieval systems based on natural user clicking
behavior, as well as to show how such methods can be practically deployed. In
particular, our focus will be on demonstrating how the Interleaving approach
and other click based techniques contrast with traditional offline evaluation,
and how these online methods can be effectively used in academic-scale
research. In addition to lecture notes, we will also provide sample software
and code walk-throughs to showcase the ease with which Interleaving and other
click-based methods can be employed by students, academics and other
researchers.
Learning more powerful test statistics for click-based retrieval evaluation
Summarization & user feedback
/
Yue, Yisong
/
Gao, Yue
/
Chapelle, Oliver
/
Zhang, Ya
/
Joachims, Thorsten
Proceedings of the 33rd Annual International ACM SIGIR Conference on
Research and Development in Information Retrieval
2010-07-19
p.507-514
Keywords: click-through data, implicit feedback, retrieval evaluation
© Copyright 2010 ACM
Summary: Interleaving experiments are an attractive methodology for evaluating
retrieval functions through implicit feedback. Designed as a blind and unbiased
test for eliciting a preference between two retrieval functions, an interleaved
ranking of the results of two retrieval functions is presented to the users. It
is then observed whether the users click more on results from one retrieval
function or the other. While it was shown that such interleaving experiments
reliably identify the better of the two retrieval functions, the naive approach
of counting all clicks equally leads to a suboptimal test. We present new
methods for learning how to score different types of clicks so that the
resulting test statistic optimizes the statistical power of the experiment.
This can lead to substantial savings in the amount of data required for
reaching a target confidence level. Our methods are evaluated on an operational
search engine over a collection of scientific articles.
Beyond position bias: examining result attractiveness as a source of
presentation bias in clickthrough data
Full papers
/
Yue, Yisong
/
Patel, Rajan
/
Roehrig, Hein
Proceedings of the 2010 International Conference on the World Wide Web
2010-04-26
v.1
p.1011-1018
Keywords: click logs, implicit feedback, presentation bias
© Copyright 2010 ACM
Summary: Leveraging clickthrough data has become a popular approach for evaluating
and optimizing information retrieval systems. Although data is plentiful, one
must take care when interpreting clicks, since user behavior can be affected by
various sources of presentation bias. While the issue of position bias in
clickthrough data has been the topic of much study, other presentation bias
effects have received comparatively little attention. For instance, since users
must decide whether to click on a result based on its summary (e.g., the title,
URL and abstract), one might expect clicks to favor "more attractive" results.
In this paper, we examine result summary attractiveness as a potential source
of presentation bias. This study distinguishes itself from prior work by aiming
to detect systematic biases in click behavior due to attractive summaries
inflating perceived relevance. Our experiments conducted on the Google web
search engine show substantial evidence of presentation bias in clicks towards
results with more attractive titles.
A support vector method for optimizing average precision
Learning to rank I
/
Yue, Yisong
/
Finley, Thomas
/
Radlinski, Filip
/
Joachims, Thorsten
Proceedings of the 30th Annual International ACM SIGIR Conference on
Research and Development in Information Retrieval
2007-07-23
p.271-278
© Copyright 2007 ACM
Summary: Machine learning is commonly used to improve ranked retrieval systems. Due
to computational difficulties, few learning techniques have been developed to
directly optimize for mean average precision (MAP), despite its widespread use
in evaluating such systems. Existing approaches optimizing MAP either do not
find a globally optimal solution, or are computationally expensive. In
contrast, we present a general SVM learning algorithm that efficiently finds a
globally optimal solution to a straightforward relaxation of MAP. We evaluate
our approach using the TREC 9 and TREC 10 Web Track corpora (WT10g), comparing
against SVMs optimized for accuracy and ROCArea. In most cases we show our
method to produce statistically significant improvements in MAP scores.
Development of a Learning-Training Simulator with Virtual Functions for
Lathe Operations
/
Li, Z.
/
Qiu, H.
/
Yue, Y.
Virtual Reality
2002-09
v.6
n.2
p.96-104
Keywords: Lathe; Machining Operations; Simulator; Skill Training; Virtual Reality
Copyright © 2002 Springer
