[1]
Using text mining to infer the purpose of permission use in mobile apps
Understanding and protecting privacy
/
Wang, Haoyu
/
Hong, Jason
/
Guo, Yao
Proceedings of the 2015 International Conference on Ubiquitous Computing
2015-09-07
p.1107-1118
© Copyright 2015 ACM
Summary: Understanding the purpose of why sensitive data is used could help improve
privacy as well as enable new kinds of access control. In this paper, we
introduce a new technique for inferring the purpose of sensitive data usage in
the context of Android smartphone apps. We extract multiple kinds of features
from decompiled code, focusing on app-specific features and text-based
features. These features are then used to train a machine learning classifier.
We have evaluated our approach in the context of two sensitive permissions,
namely ACCESS_FINE_LOCATION and READ_CONTACT_LIST, and achieved an accuracy of
about 85% and 94% respectively in inferring purposes. We have also found that
text-based features alone are highly effective in inferring purposes.
[2]
Using affective embodied agents in information literacy education
Education and collaboration
/
Guo, Yan Ru
/
Goh, Dion Hoe-Lian
/
Luyt, Brendan
JCDL'14: Proceedings of the 2014 ACM/IEEE-CS Joint Conference on Digital
Libraries
2014-09-08
p.389-398
Keywords: Computers
Keywords: Context
Keywords: Educational institutions
Keywords: Libraries
Keywords: Reliability
Keywords: Tutorials
Keywords: Affect
Keywords: Information Search Process (ISP)
Keywords: affective agents
Keywords: embodied agents
Keywords: emotions
Keywords: enjoyment
Keywords: information literacy
Keywords: information seeking
Keywords: knowledge retention
Keywords: motivation
© Copyright 2014 IEEE
Summary: This study aims to evaluate the impact of affective embodied agents (EAs) on
students' learning performance in an online tutorial that teaches academic
information seeking skills. A hundred and twenty tertiary students from two
major universities participated in the between-subjects experiment. The results
suggested that the use of affective EAs significantly increased students'
learning motivation and enjoyment, compared to neutral-EAs or text-only
conditions. However, there were no significant differences in knowledge
retention between the three groups. This study paves the way for a better
understanding of embedding affective EAs in online information literacy (IL)
education. Furthermore, the improvement in students' learning motivation and
enjoyment can serve as a basis for future research in this context.
[3]
Latent semantic sparse hashing for cross-modal similarity search
Session 4c: more hashing
/
Zhou, Jile
/
Ding, Guiguang
/
Guo, Yuchen
Proceedings of the 2014 Annual International ACM SIGIR Conference on
Research and Development in Information Retrieval
2014-07-06
p.415-424
© Copyright 2014 ACM
Summary: Similarity search methods based on hashing for effective and efficient
cross-modal retrieval on large-scale multimedia databases with massive text and
images have attracted considerable attention. The core problem of cross-modal
hashing is how to effectively construct correlation between multi-modal
representations which are heterogeneous intrinsically in the process of hash
function learning. Analogous to Canonical Correlation Analysis (CCA), most
existing cross-modal hash methods embed the heterogeneous data into a joint
abstraction space by linear projections. However, these methods fail to bridge
the semantic gap more effectively, and capture high-level latent semantic
information which has been proved that it can lead to better performance for
image retrieval. To address these challenges, in this paper, we propose a novel
Latent Semantic Sparse Hashing (LSSH) to perform cross-modal similarity search
by employing Sparse Coding and Matrix Factorization. In particular, LSSH uses
Sparse Coding to capture the salient structures of images, and Matrix
Factorization to learn the latent concepts from text. Then the learned latent
semantic features are mapped to a joint abstraction space. Moreover, an
iterative strategy is applied to derive optimal solutions efficiently, and it
helps LSSH to explore the correlation between multi-modal representations
efficiently and automatically. Finally, the unified hashcodes are generated
through the high level abstraction space by quantization. Extensive experiments
on three different datasets highlight the advantage of our method under
cross-modal scenarios and show that LSSH significantly outperforms several
state-of-the-art methods.
[4]
Design, Deployment and Evaluation of a Social Tool for Developing Effective
Working Relationships in Large Organizations
DUXU in the Enterprise
/
Karapantelakis, Athanasios
/
Guo, Yonghui
DUXU 2014: Third International Conference on Design, User Experience, and
Usability, Part IV: User Experience Design Practice
2014-06-22
v.4
p.49-60
Keywords: social media; enterprise; organizational culture
© Copyright 2014 Springer International Publishing
Summary: In an attempt to raise public awareness and promote their objectives,
organizations increasingly strive for social media presence. Similarly to using
social media tools to communicate externally, organizations are starting to
adopt such tools internally to promote information exchange. This is especially
the case for large technology companies with a skilled workforce, where
exchange of knowledge and ideas can help establish working relationships and
eventually improve organizational performance. Past experience shows that
successful adoption of social media tools differs between cases, and is closely
related to organizational culture. In this paper, we present an application
designed to arrange custom lunches between randomly-selected employees and
argue that a study of the organizational culture and subsequent application of
the findings of this study to the design of the application has contributed to
it's success. We determine success by exposing the application to trial use and
evaluating feedback from real users.
[5]
"I Have AIDS": Content analysis of postings in HIV/AIDS support group on a
Chinese microblog
/
Guo, Yanru
/
Goh, Dion Hoe-Lian
Computers in Human Behavior
2014-05
v.34
n.0
p.219-226
Keywords: Informational content
Keywords: Online support group
Keywords: People living with HIV/AIDS
Keywords: Socio-emotional content
© Copyright 2014 Elsevier Ltd.
Summary: With the widespread growth and adoption of new technologies, online
platforms such as social network sites (SNSs) have become a channel for health
information. Online groups have been set up for communication and interaction,
among which many are for people with chronic illnesses, including people with
HIV/AIDS (PHA). In the study of online communication behavior, the Social
Information Processing Theory (SIPT) predicted people will develop deeper
interpersonal relationships in online groups over time (Walther, 1996).
However, the author argued that CMC content should be examined more closely to
get a dynamic picture of how people interaction and how groups develop over
time. Thus this paper attempted to refine SIPT by enriching the framework with
detailed components, and used directed content analysis to categorize messages
posted on the PHA Support Group on Sina Weibo, a China-based microblog. The
results showed that the percentage of socio-emotional messages saw an increase
of almost 1/3 over time, taking over informational messages as the major
content in all online postings. Medical related informational messages
surpassed non-medical related informational messages as time went by. Intimacy
relationship messages saw drastic increase in the two time periods. This study
refined SIPT by providing increased granularity of its categorization scheme to
examine group communication more closely.
[6]
Similarity-based web browser optimization
Software infrastructure
/
Wang, Haoyu
/
Liu, Mengxin
/
Guo, Yao
/
Chen, Xiangqun
Proceedings of the 2014 International Conference on the World Wide Web
2014-04-07
v.1
p.575-584
© Copyright 2014 ACM
Summary: The performance of web browsers has become a major bottleneck when dealing
with complex webpages. Many calculation redundancies exist when processing
similar webpages, thus it is possible to cache and reuse previously calculated
intermediate results to improve web browser performance significantly. In this
paper, we propose a similarity-based optimization approach to improve webpage
processing performance of web browsers. Through caching and reusing of style
properties calculated previously, we are able to eliminate the redundancies
caused by processing similar webpages from the same website. We propose a
tree-structured architecture to store style properties to facilitate efficient
caching and reuse. Experiments on webpages of various websites show that the
proposed technique can speed up the webpage loading process by up to 68% and
reduce the redundant style calculations by up to 77% for the first visit to a
webpage with almost negligible overhead.
[7]
Statistical inference in two-stage online controlled experiments with
treatment selection and validation
Online experiments & advertising
/
Deng, Alex
/
Li, Tianxi
/
Guo, Yu
Proceedings of the 2014 International Conference on the World Wide Web
2014-04-07
v.1
p.609-618
© Copyright 2014 ACM
Summary: Online controlled experiments, also called A/B testing, have been
established as the mantra for data-driven decision making in many web-facing
companies. A/B Testing support decision making by directly comparing two
variants at a time. It can be used for comparison between (1) two candidate
treatments and (2) a candidate treatment and an established control. In
practice, one typically runs an experiment with multiple treatments together
with a control to make decision for both purposes simultaneously. This is known
to have two issues. First, having multiple treatments increases false positives
due to multiple comparison. Second, the selection process causes an upward bias
in estimated effect size of the best observed treatment. To overcome these two
issues, a two stage process is recommended, in which we select the best
treatment from the first screening stage and then run the same experiment with
only the selected best treatment and the control in the validation stage.
Traditional application of this two-stage design often focus only on results
from the second stage. In this paper, we propose a general methodology for
combining the first screening stage data together with validation stage data
for more sensitive hypothesis testing and more accurate point estimation of the
treatment effect. Our method is widely applicable to existing online controlled
experimentation systems.
[8]
Timeline generation with social attention
Short papers 2 -- users and interactive IR
/
Zhao, Xin Wayne
/
Guo, Yanwei
/
Yan, Rui
/
He, Yulan
/
Li, Xiaoming
Proceedings of the 2013 Annual International ACM SIGIR Conference on
Research and Development in Information Retrieval
2013-07-28
p.1061-1064
© Copyright 2013 ACM
Summary: Timeline generation is an important research task which can help users to
have a quick understanding of the overall evolution of any given topic. It thus
attracts much attention from research communities in recent years.
Nevertheless, existing work on timeline generation often ignores an important
factor, the attention attracted to topics of interest (hereafter termed "social
attention"). Without taking into consideration social attention, the generated
timelines may not reflect users' collective interests. In this paper, we study
how to incorporate social attention in the generation of timeline summaries. In
particular, for a given topic, we capture social attention by learning users'
collective interests in the form of word distributions from Twitter, which are
subsequently incorporated into a unified framework for timeline summary
generation. We construct four evaluation sets over six diverse topics. We
demonstrate that our proposed approach is able to generate both informative and
interesting timelines. Our work sheds light on the feasibility of incorporating
social attention into traditional text mining tasks.
[9]
Value Added by the Axiomatic Usability Method for Evaluating Consumer
Electronics
Business Integration
/
Guo, Yinni
/
Zhu, Yu
/
Salvendy, Gavriel
/
Proctor, Robert W.
HIMI 2013: Human Interface and the Management of Information, Part III:
Information and Interaction for Learning, Culture, Collaboration and Business
2013-07-21
v.3
p.457-466
Keywords: axiomatic evaluation; consumer electronics
© Copyright 2013 Springer-Verlag
Summary: In this paper we demonstrate how to use the axiomatic evaluation method to
evaluate usability of consumer electronic products. The axiomatic evaluation
method examines three domains of a product: customer, functional, and control
domains. This method collects not only usability problems reported by the
users, but also usability problems found through the mapping matrix between the
three domains. To determine how well this new usability evaluation method
works, an experiment was conducted to compare the axiomatic evaluation method
with a think-aloud method. 60 participants were randomly assigned to use one
method or the other to evaluate three popular consumer electronic devices.
Number of usability problems discovered and completion time were collected and
analyzed. Results showed that the axiomatic evaluation method performed better
than the think-aloud method at finding usability problems for the mobile phone
and about user expectation and control.
[10]
Take it personally: personal accountability and energy consumption in
domestic households
Sustainability
/
Guo, Yukang
/
Jones, Matt
/
Cowan, Benjamin
/
Beale, Russell
Extended Abstracts of ACM CHI'13 Conference on Human Factors in Computing
Systems
2013-04-27
v.2
p.1467-1472
© Copyright 2013 ACM
Summary: We explore the overlooked area of personal energy consumption in the context
of a shared domestic household. We discuss the potential benefits of such an
approach. We report the results of a lab study and field trial with four
households using a personal energy monitoring system. We describe the results
of the studies and discuss how such previously hidden information might raise
awareness of individual energy consumption and the benefits and problems this
entails.
[11]
Teenagers talking about technologies: designing technology to reduce teen
energy use
Sustainability
/
Bell, Beth T.
/
Toth, Nicola
/
Read, Janet C.
/
Horton, Matthew
/
Fitton, Dan
/
Little, Linda
/
Beale, Russell
/
Guo, Yukang
Extended Abstracts of ACM CHI'13 Conference on Human Factors in Computing
Systems
2013-04-27
v.2
p.1491-1496
© Copyright 2013 ACM
Summary: This paper describes the methodology through which a set of guidelines that
inform the design and development of energy-use reduction technologies for
teenagers were created. The presented research forms part of a wider project
that aims to design, develop and evaluate mobile solutions to change teen
attitudes and behavior to energy consumption. In order to understand how to
approach the design of technologies that reduce teen electricity consumption,
researchers engaged teenagers in a comprehensive user-centered evaluation of
relevant existing prototypes. The evaluation feedback was used to generate a
set of seven guidelines that will inform the design and development of future
energy-reduction devices for teenagers as part of the final stages of this
overall research project.
[12]
Parallel proximal support vector machine for high-dimensional pattern
classification
Knowledge management poster session
/
Zhu, Zhenfeng
/
Zhu, Xingquan
/
Ye, Yangdong
/
Guo, Yue-Fei
/
Xue, Xiangyang
Proceedings of the 2012 ACM Conference on Information and Knowledge
Management
2012-10-29
p.2351-2354
© Copyright 2012 ACM
Summary: Proximal support vector machine (PSVM) is a simple but effective classifier,
especially for solving large-scale data classification problems. An inherent
deficiency of PSVM lies on its inefficiency for dealing with high-dimensional
data. In this paper, we propose a parallel version of PSVM (PPSVM). Based on
random dimensionality partitioning, PPSVM can obtain partitioned local model
parameters in parallel, with combined parameters to form the final global
solution. In fact, PPSVM enjoys two properties: 1) It can calculate model
parameters in parallel and is therefore a fast learning method with
theoretically proved convergence; and 2) It can avoid the inversion of large
matrix, which makes it suitable for high-dimensional data. In the paper, we
also propose a random PPSVM with randomly partitioned data in each iteration to
improve the performance of PSVM. Experimental results on real-world data
demonstrate that the proposed methods can obtain similar or even better
prediction accuracy than PSVM with much better runtime efficiency.
[13]
On top-k recommendation using social networks
Social recommendation
/
Yang, Xiwang
/
Steck, Harald
/
Guo, Yang
/
Liu, Yong
Proceedings of the 2012 ACM Conference on Recommender Systems
2012-09-09
p.67-74
© Copyright 2012 ACM
Summary: Recommendation accuracy can be improved by incorporating trust relationships
derived from social networks. Most recent work on social network based
recommendation is focused on minimizing the root mean square error (RMSE).
Social network based top-k recommendation, which recommends to a user a small
number of items at a time, is not well studied. In this paper, we conduct a
comprehensive study on improving the accuracy of top-k recommendation using
social networks. We first show that the existing social-trust enhanced Matrix
Factorization (MF) models can be tailored for top-k recommendation by including
observed and missing ratings in their training objective functions. We also
propose a Nearest Neighbor (NN) based top-k recommendation method that combines
users' neighborhoods in the trust network with their neighborhoods in the
latent feature space. Experimental results on two publicly available datasets
show that social networks can significantly improve the top-k hit ratio,
especially for cold start users. Surprisingly, we also found that the technical
approach for combining feedback data (e.g. ratings) with social network
information that works best for minimizing RMSE works poorly for maximizing the
hit ratio, and vice versa.
[14]
Teenagers talking about energy: using narrative methods to inform design
Work-in-progress
/
Toth, Nicola
/
Little, Linda
/
Read, Janet
/
Guo, Yukang
/
Fitton, Daniel
/
Horton, Matthew
Extended Abstracts of ACM CHI'12 Conference on Human Factors in Computing
Systems
2012-05-05
v.2
p.2171-2176
© Copyright 2012 ACM
Summary: This paper explores teenagers' attitudes towards energy consumption. The
research is part of a wider project with the goal of designing, developing and
evaluating mobile solutions to change teenagers' attitudes and behaviour
towards energy. Diaries, stories, written scenarios and focus groups provided
initial insight into teenagers' attitudes. The use of multiple methods engaged
teenagers in the project and resulted in data that was rich in detail and
context. Initial themes that emerged for the data were: type of energy used,
impact of energy use, sources of information, location and green teens.
Findings will inform the design of mobile solutions for teenagers and help in
the development of a behavioural change programme.
[15]
Constructing the Cool Wall: A Tool to Explore Teen Meanings of Cool
/
Fitton, Dan
/
Read, Janet C.
/
Horton, Matthew
/
Little, Linda
/
Toth, Nicola
/
Guo, Yukang
PsychNology Journal
2012
v.10
n.2
p.141-162
Keywords: Teenagers, cool, interaction design
© Copyright 2012 Authors
Summary: This paper describes the development and exploration of a tool designed to
assist in investigating 'cool' as it applies to the design of interactive
products for teenagers. The method involved the derivation of theoretical
understandings of cool from literature that resulted in identification of seven
core categories for cool, which were mapped to a hierarchy. The hierarchy
includes having of cool things, the doing of cool activities and the being of
cool. This paper focuses on a tool, the Cool Wall, developed to explore one
specific facet of the hierarchy; exploring shared understanding of having cool
things. The paper describes the development and construction of the tool, using
a heavily participatory approach, and the results and analysis of three
studies. The first study was carried out over 2 days in a school in the UK. The
results of the study both provide clear insights into cool things and enable a
refined understanding of cool in this context. Two additional studies are then
used to identify potential shortcomings in the Cool Wall methodology. In the
second study participants were able to populate a paper cool wall with anything
they chose, this revealed two potential new categories of images and that the
current set of images covered the majority of key themes. In the third study
teenagers interpretations of the meaning of the images included in the Cool
Wall were explored, this showed that the majority of meanings were as expected
and a small number of unexpected interpretations provided some valuable
insights.
[16]
Transfer active learning
Poster session: knowledge management
/
Zhu, Zhenfeng
/
Zhu, Xingquan
/
Ye, Yangdong
/
Guo, Yue-Fei
/
Xue, Xiangyang
Proceedings of the 2011 ACM Conference on Information and Knowledge
Management
2011-10-24
p.2169-2172
© Copyright 2011 ACM
Summary: Active learning traditionally assumes that labeled and unlabeled samples are
subject to the same distributions and the goal of an active learner is to label
the most informative unlabeled samples. In reality, situations may exist that
we may not have unlabeled samples from the same domain as the labeled samples
(i.e. target domain), whereas samples from auxiliary domains might be
available. Under such situations, an interesting question is whether an active
learner can actively label samples from auxiliary domains to benefit the target
domain. In this paper, we propose a transfer active learning method, namely
Transfer Active SVM (TrAcSVM), which uses a limited number of target instances
to iteratively discover and label informative auxiliary instances. TrAcSVM
employs an extended sigmoid function as instance weight updating approach to
adjust the models for prediction of (newly arrived) target data. Experimental
results on real-world data sets demonstrate that TrAcSVM obtains better
efficiency and prediction accuracy than its peers.
[17]
A Conceptual Model of the Axiomatic Usability Evaluation Method
Information and User Interfaces Design
/
Guo, Yinni
/
Proctor, Robert W.
/
Salvendy, Gavriel
HIMI 2011: Human Interface and the Management of Information, Symposium on
Human Interface, Part I: Interacting with Information
2011-07-09
v.1
p.93-102
Keywords: axiomatic design; usability engineering
Copyright © 2011 Springer-Verlag
Summary: This paper describes a new usability evaluation method developed for
consumer electronics. This method, Axiomatic Evaluation, is based on Axiomatic
Design theory, a formalized methodology that can be used to represent a variety
of design problems. From this perspective, to generate a design that meets the
perceived needs, designers should first specify the design goals of "what we
want to achieve", and then start the design process with a clear description of
"how we will achieve it", so that the recursive "design/build/test" cycle could
be reduced.
[18]
Understanding and designing cool technologies for teenagers
Works-in-progress
/
Read, Janet
/
Fitton, Daniel
/
Cowan, Benjamin
/
Beale, Russell
/
Guo, Yukang
/
Horton, Matthew
Proceedings of ACM CHI 2011 Conference on Human Factors in Computing Systems
2011-05-07
v.2
p.1567-1572
© Copyright 2011 ACM
Summary: This paper describes how initial principles for the designs of an
interactive application were informed from a study of 'coolness' with two
different ages of teenagers. The study used drawings to examine how teenagers
might design their environments and these were then analysed by the research
team based on a set of characteristics of cool that were drawn from the
literature. Results from the teenagers' drawings demonstrate some change in
emphasis between the younger and older age groups and between the genders. A
design space around innovation and rebellion is implicated in the findings.
[19]
Spreading the word: the proliferation of research using social networks
Posters
/
Seymour, Joshua
/
Stanton, Jeffery
/
Guo, Yuanying
Proceedings of the 2011 iConference
2011-02-08
p.767-769
© Copyright 2011 ACM
Summary: This poster presents the initial findings of an approach used to analyze a
faculty member's direct and relevant indirect networks in order to develop
connections with academic peers of similar research interests to expand the
visibility and awareness of the faculty member's research through the use of an
online collaborative group. It is anticipated that by developing this group,
where sharing of publications and ideas is promoted, that the faculty member
will increase their virtual research footprint through the awareness and
referencing of their publications.
[20]
Content information desired by Chinese users for effective use of
information appliances
/
Guo, Yinni
/
Salvendy, Gavriel
/
Proctor, Robert W.
Computers in Human Behavior
2010-11
v.26
n.6
p.1685-1693
Keywords: Content preparation
Keywords: Mobile phone
Keywords: Survey
Keywords: Factor analysis
Keywords: Information appliance
© Copyright 2010 Elsevier Ltd.
Summary: Many studies have been conducted to determine how to present information on
mobile phones in such a way as to enhance usability, but those studies have not
considered what information users need for effective decision making. To
investigate what users want from mobile phones, we carried out a content
preparation study. A questionnaire was constructed based on prior results from
website content research, traditional usability studies on consumer
electronics, and extensive study on various types of mobile phones; it was
completed by 375 Chinese industrial participants. The statistical results
revealed nine major factors of mobile phone content: information relating to
input/search, functions, operation, multimedia functions, stored files, phone
calls, help/service, accessory functions, and messages. Also, users of
different ages and genders evidenced different requirements for mobile phone
content, especially concerning accessory and multimedia functions. This study
suggests guidelines for mobile phone designers targeted at the Chinese market
and provides a base for content study of other information appliances.
[21]
Transfer incremental learning for pattern classification
Poster session 3: KM track
/
Zhu, Zhenfeng
/
Zhu, Xingquan
/
Guo, Yue-Fei
/
Xue, Xiangyang
Proceedings of the 2010 ACM Conference on Information and Knowledge
Management
2010-10-26
p.1709-1712
© Copyright 2010 ACM
Summary: Traditional machine learning methods, such as Support Vector Machines
(SVMs), usually assume that training and test data share the same
distributions. Due to the inherent dynamic data nature, it is often observed
that (1) the volumes of the training data may gradually grow; and (2) the
existing and the newly arrived samples may be subject to different
distributions or learning tasks. In this paper, we propose a Transfer
Incremental Support Vector Machine (TrISVM), with the objective of tackling
changes in data volumes and learning tasks at the same time. By using new
updating rules to calculate the inverse matrix, TrISVM solves the existing
incremental learning problem more efficiently, especially for high dimensional
data. Furthermore, when using new samples to update the existing models, TrISVM
employs sample-based weight adjustment procedures to ensure that the concept
transferring between auxiliary and target samples can be leveraged to fulfill
the transfer learning goal. Experimental results on real-world data sets
demonstrate that TrISVM achieves better efficiency and prediction accuracy than
both incremental-learning and transfer-learning based methods. In addition, the
results also show that TrISVM is able to achieve bidirectional knowledge
transfer between two similar tasks.
[22]
FALCON: seamless access to meeting data from the inbox and calendar
Demo session 2: KM and DB
/
Bjellerup, Peter
/
Cama, Karl J.
/
Desikan, Mukundan
/
Guo, Yi
/
Kale, Ajinkya G.
/
Lai, Jennifer C.
/
Lethif, Nizar
/
Lu, Jie
/
Topkara, Mercan
/
Wissel, Stephan H.
Proceedings of the 2010 ACM Conference on Information and Knowledge
Management
2010-10-26
p.1951-1952
© Copyright 2010 ACM
Summary: We present a system that supports seamless access to information contained
in recorded meetings from the cornerstone points of a knowledge worker's daily
life: mailbox and calendar. The solution supports granular search of meeting
content from an enterprise email system and automatically displays recordings
of meetings related to the message the user is currently viewing. Additionally
thumbnail summaries of the meetings are added to the user's calendar entries
after the meetings have taken place. Lastly our system supports easy sharing of
videos associated with recorded meetings through the use of hot-linked
thumbnail summaries which can be sent via email.
[23]
Acoustic source localization of everyday sounds using wireless sensor
networks
Posters
/
Guo, Yukang
/
Hazas, Mike
Proceedings of the 2010 International Conference on Ubiquitous Computing
2010-09-26
p.411-412
Keywords: acoustic source localization, audio classification
© Copyright 2010 ACM
Summary: Acoustic events are a rich source of information for context-awareness and
support various application areas, such as audio surveillance [1], sound
sensing [2], intelligent auditory interfaces [3] and speech localization [4].
Acoustic localization solutions are also increasingly becoming important and
feasible due to recent advances in personal portable computing devices (e.g.
smart phones, PDAs and laptops), where rapidly deployable distributed
fine-grain acoustic localization systems can help to locate mobile users and
devices for using in location-aware interfaces and applications. However, while
a number of acoustic localization systems have been proposed over the last few
decades, these generally require the use of expensive dedicated microphone
arrays and have been developed only for a single or limited number of acoustic
events, tailored to specific scenarios. Many different types of acoustic events
exist in our everyday environments, hence, in this work we address the general
problem of how to localize multiple classes of acoustic events in a distributed
sensor environment. We propose a framework for detecting and locating events
(e.g., speech, clicks, footsteps, or the sound of an object put down on a
table) according to generic acoustic characteristics and present a preliminary
evaluation.
[24]
Topic-based personalized recommendation for collaborative tagging system
Recommenders
/
Guo, Yanhui
/
Joshi, James B. D.
Proceedings of the 21st ACM Conference on Hypertext and Hypermedia
2010-06-29
p.61-66
Keywords: collaborative tagging, latent topic models, personalization, recommendation
© Copyright 2010 ACM
Summary: Collaborative tagging has become a very popular way to share, annotate, and
discover online resources in Web 2.0. Yet as the number of resources in
Collaborative tagging system grows over time, sifting through the large amounts
of resources and finding the right resources to recommend to the right user is
becoming a challenging problem. In this paper, we investigate a probabilistic
generative model for collaborative tagging, explore the implicit semantic
connections in the sparse and noisy information space of heterogeneous users
and unsupervised tagging. First, a modified Latent Dirichlet Allocation (LDA)
model is used to cluster the tags and users simultaneously. The generalization
of resource description and user could alleviate the tag noise and data
sparseness of recommendation effectively. And then, considering that
topic-based recommendation only takes the users' global interest into
consideration without the capability of distinguishing users' interest in
detail, we combine the global interests with the individual interest and
community interest. Experimental results demonstrate the topic-based
personalized recommendation method, which integrate both the commonality factor
among users and the specialties of individuals, could alleviate data sparsity
and provide a more flexible and effective recommendation than previous methods.
[25]
What Do Users Want to See? A Content Preparation Study for Consumer
Electronics
User Studies
/
Guo, Yinni
/
Proctor, Robert W.
/
Salvendy, Gavriel
HCI International 2009: 13th International Conference on Human-Computer
Interaction, Part I: New Trends
2009-07-19
v.1
p.413-420
Keywords: Content preparation; factor structure; consumer electronics
Copyright © 2009 Springer-Verlag
Summary: To investigate what users want to see from consumer electronic devices, a
content preparation study was conducted. A questionnaire was constructed based
on the results from web site content research and traditional usability studies
on consumer electronics, and was completed by 401 Chinese participants. The
statistical results reveal that there are nine major factors of cell phone
content. Also users of different age and gender have different requirements for
cell phone content, especially concerning accessory and multimedia functions.
This study suggests guidelines for cell phone designers targeted at the Chinese
market, as well as a base for content study of other consumer electronics.
