[1]
Mixed-Initiative Real-Time Topic Modeling & Visualization for Crisis
Counseling
Affect / Health
/
Dinakar, Karthik
/
Chen, Jackie
/
Lieberman, Henry
/
Picard, Rosalind
/
Filbin, Robert
Proceedings of the 2015 International Conference on Intelligent User
Interfaces
2015-03-29
v.1
p.417-426
© Copyright 2015 ACM
Summary: Text-based counseling and support systems have seen an increasing
proliferation in the past decade. We present Fathom, a natural language
interface to help crisis counselors on Crisis Text Line, a new 911-like crisis
hotline that takes calls via text messaging rather than voice. Text messaging
opens up the opportunity for software to read the messages as well as people,
and to provide assistance for human counselors who give clients emotional and
practical support. Crisis counseling is a tough job that requires dealing with
emotionally stressed people in possibly life-critical situations, under time
constraints. Fathom is a system that provides topic modeling of calls and
graphical visualization of topic distributions, updated in real time. We
develop a mixed-initiative paradigm to train coherent topic and word
distributions and use them to power real-time visualizations aimed at reducing
counselor cognitive overload. We believe Fathom to be the first real-time
computational framework to assist in crisis counseling.
[2]
Steptorials: mixed-initiative learning of high-functionality applications
Posters
/
Lieberman, Henry
/
Rosenzweig, Elizabeth
/
Fry, Christopher
Proceedings of the 2014 International Conference on Intelligent User
Interfaces
2014-02-24
v.1
p.359-364
© Copyright 2014 ACM
Summary: How can a new user learn an unfamiliar application, especially if it is a
high-functionality (hi-fun) application, like Photoshop, Excel, or programming
language IDE. Many applications provide introductory videos, illustrative
examples, and documentation on individual operations. Tests show, however, that
novice users are likely to ignore the provided help, and try to learn by
exploring the application first. In a hi-fun application, though, the user may
lack understanding of the basic concepts of an application's operation, even
though they were likely explained in the (ignored) documentation. This paper
introduces steptorials ("stepper tutorials"), a new interaction strategy for
learning hi-fun applications. A steptorial aims to teach the user how to work
through a simple, but nontrivial, example of using the application. Steptorials
are unique because they allow varying the autonomy of the user at every step. A
steptorial has a control structure of a reversible programming language
stepper. The user may choose, at any time, to be shown how to do a step, be
guided through it, use the application interface without constraint, or to
return to a previous step. It reduces the risk in either trying new operations
yourself, or conversely, the risk of ceding control to the computer. It
introduces a new paradigm of mixed-initiative learning of application
interfaces.
[3]
Crowdsourced ethics with personalized story matching
Learning
/
Lieberman, Henry
/
Dinakar, Karthik
/
Jones, Birago
Extended Abstracts of ACM CHI'13 Conference on Human Factors in Computing
Systems
2013-04-27
v.2
p.709-714
© Copyright 2013 ACM
Summary: Cyberbullying is a widespread and growing social problem, threatening the
viability of social networks for youth. We believe that one of the best ways to
combat this problem is to use these incidents as "teaching moments",
encouraging teens to reflect on their behavior and choices. Sites that offer
community discussions around the ethical aspects of social situations can help
teens feel less alone in their plight, and provide useful advice and emotional
support. But the success of these "crowdsourced ethics" sites depends
critically on the user feeling like discussions are relevant to their own
personal experience.
We have augmented the crowdsourced ethics site "Over The Line", offered by
MTV Networks, with a personalized story matcher that classifies stories
according to dynamically discovered high-level themes like "sending nude
pictures online" or "feeling pressure in relationships". The matcher uses a
mixed-initiative LDA machine learning technique [2], and a commonsense
knowledge base specialized to the bullying problem. The site is currently
public, and attracts an audience of thousands of users daily.
[4]
Script-based story matching for cyberbullying prevention
Social computing
/
Macbeth, Jamie
/
Adeyema, Hanna
/
Lieberman, Henry
/
Fry, Christopher
Extended Abstracts of ACM CHI'13 Conference on Human Factors in Computing
Systems
2013-04-27
v.2
p.901-906
© Copyright 2013 ACM
Summary: While the Internet and social media help keep today's youth better connected
to their friends, family, and community, the same media are also the form of
expression for an array of harmful social behaviors, such as cyberbullying and
cyber-harassment. In this paper we present work in progress to develop
intelligent interfaces to social media that use commonsense knowledge bases and
automated narrative analyses of text communications between users to trigger
selective interventions and prevent negative outcomes. While other approaches
seek merely to classify the overall topic of the text, we try to match stories
to finer-grained ''scripts' that represent stereotypical events and actions.
For example, many bullying stories can be matched to a ''revenge' script that
describes trying to harm someone who has harmed you. These tools have been
implemented in an initial prototype system and tested on a database of real
stories of cyberbullying collected on MTV's ''A Thin Line' Web site.
[5]
Introduction to the Special Issue on Common Sense for Interactive Systems
/
Lieberman, Henry
/
Havasi, Catherine
ACM Transactions on Interactive Intelligent Systems
2012-09
v.2
n.3
p.14
© Copyright 2012 ACM
Summary: This editorial introduction describes the aims and scope of the special
issue on Common Sense for Interactive Systems of the ACM Transactions on
Interactive Intelligent Systems. It explains why the common sense knowledge
problem is crucial for both artificial intelligence and human-computer
interaction, and it shows how the four articles selected for this issue fit
into the theme.
[6]
Common Sense Reasoning for Detection, Prevention, and Mitigation of
Cyberbullying
/
Dinakar, Karthik
/
Jones, Birago
/
Havasi, Catherine
/
Lieberman, Henry
/
Picard, Rosalind
ACM Transactions on Interactive Intelligent Systems
2012-09
v.2
n.3
p.18
© Copyright 2012 ACM
Summary: Cyberbullying (harassment on social networks) is widely recognized as a
serious social problem, especially for adolescents. It is as much a threat to
the viability of online social networks for youth today as spam once was to
email in the early days of the Internet. Current work to tackle this problem
has involved social and psychological studies on its prevalence as well as its
negative effects on adolescents. While true solutions rest on teaching youth to
have healthy personal relationships, few have considered innovative design of
social network software as a tool for mitigating this problem. Mitigating
cyberbullying involves two key components: robust techniques for effective
detection and reflective user interfaces that encourage users to reflect upon
their behavior and their choices.
Spam filters have been successful by applying statistical approaches like
Bayesian networks and hidden Markov models. They can, like Google's GMail,
aggregate human spam judgments because spam is sent nearly identically to many
people. Bullying is more personalized, varied, and contextual. In this work, we
present an approach for bullying detection based on state-of-the-art natural
language processing and a common sense knowledge base, which permits
recognition over a broad spectrum of topics in everyday life. We analyze a more
narrow range of particular subject matter associated with bullying (e.g.
appearance, intelligence, racial and ethnic slurs, social acceptance, and
rejection), and construct BullySpace, a common sense knowledge base that
encodes particular knowledge about bullying situations. We then perform joint
reasoning with common sense knowledge about a wide range of everyday life
topics. We analyze messages using our novel AnalogySpace common sense reasoning
technique. We also take into account social network analysis and other factors.
We evaluate the model on real-world instances that have been reported by users
on Formspring, a social networking website that is popular with teenagers.
On the intervention side, we explore a set of reflective user-interaction
paradigms with the goal of promoting empathy among social network participants.
We propose an "air traffic control"-like dashboard, which alerts moderators to
large-scale outbreaks that appear to be escalating or spreading and helps them
prioritize the current deluge of user complaints. For potential victims, we
provide educational material that informs them about how to cope with the
situation, and connects them with emotional support from others. A user
evaluation shows that in-context, targeted, and dynamic help during
cyberbullying situations fosters end-user reflection that promotes better
coping strategies.
[7]
Textual tinkerability: encouraging storytelling behaviors to foster emergent
literacy
Case studies
/
Chang, Angela
/
Breazeal, Cynthia
/
Faridi, Fardad
/
Roberts, Tom
/
Davenport, Glorianna
/
Lieberman, Henry
/
Montfort, Nick
Extended Abstracts of ACM CHI'12 Conference on Human Factors in Computing
Systems
2012-05-05
v.2
p.505-520
© Copyright 2012 ACM
Summary: This paper presents textual tinkerability, a new concept for fostering early
literacy skills during parent-child reading. Textual tinkerability maps
storytelling gestures to changes in animation and text to assist reading
exploration and demonstration of the link between text, spoken word, and
concept. TinkRBooks are flexible tablet-based storybooks that allow readers to
actively explore concepts in text using textual tinkerability. When reading
TinkRBooks, both parents and children can alter text (character attributes and
parts of speech) by manipulating story elements (props and characters) as they
read. We demonstrate how textual tinkerability encourages more dialog, print
referencing and dialogic questioning between parent-child dyads in shared
reading as compared to paper books. In addition, our study reports observations
of storytelling performance behaviors that foster playful and socially intimate
shared reading behaviors that are closely mapped to the teaching and learning
of emergent literacy skills.
[8]
Raconteur: integrating authored and real-time social media
Organizations & enterprise
/
Chi, Pei-Yu
/
Lieberman, Henry
Proceedings of ACM CHI 2011 Conference on Human Factors in Computing Systems
2011-05-07
v.1
p.3165-3168
© Copyright 2011 ACM
Summary: Social media enables people to share personal experiences, often through
real-time media such as chat. People also record their life experiences in
media collections, with photos and video. However, today's social media force a
choice between real-time communication, and authoring a coherent story
illustrated with digital media. There is simply not enough time in real-time
communication to select and compose coherent multimedia stories.
We present Raconteur, which introduces a new style of social media combining
aspects of the real-time and authored styles of communication. It is structured
around a text chat, augmented by an agent that continuously interprets the chat
text to suggest appropriate media elements to illustrate the story. A small
experiment shows that storytellers find Raconteur's suggestions helpful in
presenting their experiences, and audiences find the interaction engaging.
[9]
Intelligent assistance for conversational storytelling using story patterns
Intelligent authoring and information presentation
/
Chi, Pei-Yu
/
Lieberman, Henry
Proceedings of the 2011 International Conference on Intelligent User
Interfaces
2011-02-13
p.217-226
© Copyright 2011 ACM
Summary: People who are not professional storytellers usually have difficulty
composing travel photos and videos from a mundane slideshow into a coherent and
engaging story, even when it is about their own experiences. However, consider
putting the same person in a conversation with a friend -- suddenly the story
comes alive.
We present Raconteur 2, a system for conversational storytelling that
encourages people to make coherent points, by instantiating large-scale story
patterns and suggesting illustrative media. It performs natural language
processing in real-time on a text chat between a storyteller and a viewer and
recommends appropriate media items from a library. Each item is annotated with
one or a few sentences in unrestricted English. A large commonsense knowledge
base and a novel commonsense inference technique are used to identify story
patterns such as problem and resolution or expectation violation. It uses a
concept vector representation that goes beyond keyword matching or word
co-occurrence based techniques. A small experiment shows that people find
Raconteur's interaction design engaging, and suggestions helpful for real-time
storytelling.
[10]
Sleep Across Military Environments
GENERAL SESSION: GS8 -- Sleep Across Military Environments
/
Alfred, Petra
/
Boykin, Gary
/
Caldwell, Lynn
/
Lieberman, Harris
/
Matsangas, Panigiotis
/
Miller, Nita Lewis
/
Rice, Valerie
/
Nancy, ?
Proceedings of the Human Factors and Ergonomics Society 54th Annual Meeting
2010-09-27
v.54
p.769-773
© Copyright 2010 HFES
Summary: This focus of this discussion panel is on the effect of sleep on human
performance in different military environments or contexts. Panelists will
discuss a wide range of topics including how to address fatigue among Air Force
pilots, the impact of sleep on performance in Army Advanced Individual
Training, the effects of adjusting Army and Navy recruits' sleep schedules
during training, the existing gaps in addressing sleep needs on naval vessels,
the impact of sleep loss and other stressors on dismounted warfighter
performance, and the effects of chronic inadequate sleep on cognitive
readiness. It is important to understand both the differences in the effects of
sleep in these environments, as well as the commonalities that can be applied
to multiple environments and operators. Our panelists include some of the
foremost sleep experts of today, as well as others who examine sleep in their
human performance research. Participation in this panel will include discussing
their latest research, offering practical applications, and engaging the
audience in discussions of cross-disciplinary applications, including areas for
collaboration across military and civilian services and environments. Finally,
panelists and audience members will and share ideas about directions for future
sleep-related research.
[11]
Raconteur: from intent to stories
Short paper presentations (posters)
/
Chi, Pei-Yu
/
Lieberman, Henry
Proceedings of the 2010 International Conference on Intelligent User
Interfaces
2010-02-07
p.301-304
Keywords: commonsense computing, media editing, photograph, story analogy, story goal,
storytelling, video
© Copyright 2010 ACM
Summary: When editing a story from a large collection of media, such as photos and
video clips captured from daily life, it is not always easy to understand how
particular scenes fit into the intent for the overall story. Especially for
novice editors, there is often a lack of coherent connections between scenes,
making it difficult for the viewers to follow the story.
In this paper, we present Raconteur, a story editing system that helps users
assemble coherent stories from media elements, each annotated with a sentence
or two in unrestricted natural language. It uses a Commonsense knowledge base,
and the AnalogySpace Commonsense reasoning technique. Raconteur focuses on
finding story analogies -- different elements illustrating the same overall
"point", or independent stories exhibiting similar narrative structures.
[12]
The why UI: using goal networks to improve user interfaces
Short paper presentations (posters)
/
Smith, Dustin A.
/
Lieberman, Henry
Proceedings of the 2010 International Conference on Intelligent User
Interfaces
2010-02-07
p.377-380
Keywords: goal networks, learning goal networks, plan recognition, to-do list
© Copyright 2010 ACM
Summary: People interact with interfaces to accomplish goals, and knowledge about
human goals can be useful for building intelligent user interfaces. We suggest
that modeling high, human-level goals like "repair my credit score", is
especially useful for coordinating workflows between interfaces, automated
planning, and building introspective applications.
We analyzed data from 43Things.com, a website where users share and discuss
goals and plans in natural language, and constructed a goal network that
relates what goals people have with how people solve them. We then label goals
with specific details, such as where the goal typically is met and how long it
takes to achieve, facilitating plan and goal recognition. Lastly, we
demonstrate a simple application of goal networks, deploying it in a mobile,
location-aware to-do list application, ToDoGo, which uses goal networks to help
users plan where and when to accomplish their desired goals.
[13]
Finding your way in a multi-dimensional semantic space with luminoso
Short paper presentations (posters)
/
Speer, Robert H.
/
Havasi, Catherine
/
Treadway, K. Nichole
/
Lieberman, Henry
Proceedings of the 2010 International Conference on Intelligent User
Interfaces
2010-02-07
p.385-388
Keywords: common sense, n-dimensional visualization, natural language processing, svd
© Copyright 2010 ACM
Summary: In AI, we often need to make sense of data that can be measured in many
different dimensions -- thousands of dimensions or more -- especially when this
data represents natural language semantics. Dimensionality reduction techniques
can make this kind of data more understandable and more powerful, by projecting
the data into a space of many fewer dimensions, which are suggested by the
computer. Still, frequently, these results require more dimensions than the
human mind can grasp at once to represent all the meaningful distinctions in
the data.
We present Luminoso, a tool that helps researchers to visualize and
understand a multi-dimensional semantic space by exploring it interactively. It
also streamlines the process of creating such a space, by inputting text
documents and optionally including common-sense background information. This
interface is based on the fundamental operation of "grabbing" a point, which
simultaneously allows a user to rotate their view using that data point, view
associated text and statistics, and compare it to other data points. This also
highlights the point's neighborhood of semantically-associated points,
providing clues for reasons as to why the points were classified along the
dimensions they were. We show how this interface can be used to discover trends
in a text corpus, such as free-text responses to a survey.
[14]
EDITED BOOK
No Code Required: Giving Users Tools to Transform the Web
/
Cypher, Allen
/
Dontcheva, Mira
/
Lau, Tessa
/
Nichols, Jeffrey
2010
p.512
Morgan Kaufmann Publishers
Introduction
End User Programming on the Web
+ Cypher, Allen
Why We Customize the Web
+ Miller, Robert
I. End User Programming Languages for the Web
Sloppy Programming
+ Little, Greg
Mixing the reactive with the personal: Opportunities for end user programming in Personal information management (system)
+ Van Kleek, Max
Going beyond PBD: A Play-by-Play and Mixed-initiative Approach (system)
+ Jung, Hyuckchul
Rewriting the Web with Chickenfoot (system)
+ Miller, Robert
A Goal-Oriented Web Browser (system)
+ Faaborg, Alexander
II. Systems and Applications
Clip, Connect, Clone: Combining Application Elements to Build Custom Interfaces for Information Access (system)
+ Fujima, Jun
Mash Maker (system)
+ Ennals, Robert
Collaborative scripting on the web (system)
+ Lau, Tessa
Programming by a Sample: Rapidly Creating Web Applications with d.mix (system)
+ Hartmann, Björn
Highlight: End User Mobilization of Existing Web Sites (system)
+ Nichols, Jeffrey
Subjunctive Interfaces for the Web
+ Lunzer, Aran
From Web Summaries to Search Templates: Automation for Personal Web Content (system)
+ Dontcheva, Mira
Access to the Temporal Web Through Zoetrope (system)
+ Adar, Eytan
Enabling End Users to Independently Build Accessibility into the Web
+ Bigham, Jeffrey
Social Accessibility: A Collaborative Approach For Improving Web Accessibility (system)
+ Borodin, Yevgen
III. Data Management and Interoperability
A World Wider than the Web: End User Programming Across Multiple Domains (system)
+ Haines, Will
Knowing What You're Talking About: Natural Language Programming of a Multi-Player Online Game (system)
+ Lieberman, Henry
IV. User Studies
Mashups for Web-Active End Users
+ Zang, Nan
Mashed layers and muddled models: debugging mashup applications
+ Jones, M. Cameron
Reuse in the world of end-user programmers
+ Scaffidi, Christopher
Using Web Search to Write Programs
+ Brandt, Joel
[15]
PerspectiveSpace: Opinion Modeling with Dimensionality Reduction
Peer-reviewed Papers
/
Alonso, Jason B.
/
Havasi, Catherine
/
Lieberman, Henry
Proceedings of the 2009 Conference on User Modeling, Adaptation and
Personalization
2009-06-22
p.162-172
© Copyright 2009 Springer-Verlag
Summary: Words mean different things to different people, and capturing these
differences is often a subtle art. These differences are often "a matter of
perspective". Perspective can be taken to be the set of beliefs held by a
person as a result of their background, culture, tastes, and experience. But
how can we represent perspective computationally?
In this paper, we present PerspectiveSpace, a new technique for modeling
spaces of users and their beliefs. PerspectiveSpace represents these spaces as
a matrix of users, and data on how people agree or disagree on assertions that
they themselves have expressed. It uses Principal Component Analysis (PCA) to
reduce the dimensionality of that matrix, discovering the most important axes
that best characterize the space. It can then express user perspectives and
opinions in terms of these axes. For recommender systems, because it discovers
patterns in the beliefs about items, rather than similarity of the items or
users themselves, it can perform more nuanced categorization and
recommendation. It integrates with our more general common sense reasoning
technique, AnalogySpace, which can reason over the content of expressed
opinions.
An application of PerspectiveSpace to movie recommendation, 2-wit, is
presented. A leave-one-out test shows that PerspectiveSpace captures the
consistency of users' opinions very well. The technique also has applications
ranging from discovering subcultures in a larger society, to building
community-driven web sites.
[16]
What's next?: emergent storytelling from video collection
Looking at videos
/
Shen, Edward Yu-Te
/
Lieberman, Henry
/
Davenport, Glorianna
Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems
2009-04-04
v.1
p.809-818
Keywords: emergent storytelling, interactive storytelling, storied navigation
© Copyright 2009 ACM
Summary: In the world of visual storytelling, narrative development relies on a
particular temporal ordering of shots and sequences and scenes. Rarely is this
ordering cast in stone. Rather, the particular ordering of a story reflects a
myriad of interdependent decisions about the interplay of structure, narrative
arc and character development. For storytellers, particularly those developing
their narratives from large documentary archives, it would be helpful to have a
visualization system partnered with them to present suggestions for the most
compelling story path.
We present Storied Navigation, a video editing system that helps authors
compose a sequence of scenes that tell a story, by selecting from a corpus of
annotated clips. The clips are annotated in unrestricted natural language.
Authors can also type a story in unrestricted English, and the system finds
possibilities for clips that best match high-level elements of the story.
Beyond simple keyword matching, these elements can include the characters,
emotions, themes, and story structure. Authors can also interactively replace
existing scenes or predict the next scene to continue a story, based on these
characteristics. Storied Navigation gives the author the feel of brainstorming
about the story rather than simply editing the media.
[17]
Breaking down brick walls: design, construction, and prototype fabrication
knowledge in architecture
Spotlight on work in progress session 2
/
Villalon, Rachelle
/
Lieberman, Henry
/
Sass, Larry
Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems
2009-04-04
v.2
p.4261-4266
Keywords: architectural design tools and methodology, architecture and design,
commonsense reasoning, digital fabrication, goal oriented interfaces, robotics
© Copyright 2009 ACM
Summary: Architectural designs are not just collections of 3D objects. Architects
have both high-level aesthetic design intent, and intent for the functionality
of the building; these must eventually translate into real-world construction
materials and processes. Physical prototypes are still essential for the
architect and their clients to get a feel for whether designs "work". An
exciting recent development in architecture is the use of industrial robots to
automatically construct 3D prototype architectural models. But programming the
robots requires tedious procedures of low-level commands, far removed from the
designer's intent.
Adeon is a system that integrates high-level architectural design knowledge,
including aesthetic and stylistic intent, with knowledge about materials and
construction processes, and robot programming code for constructing prototype
3D physical models. It centers around collecting and associating "common sense"
knowledge, expressed in English and converted to a knowledge representation
about the various levels. It provides a graphic editor that allows architects
to draw high-level aesthetic designs, perhaps referencing known styles or
historical examples, and retrieving relevant construction, materials, and cost
information. It automatically produces a robot program for constructing the
prototype. We present examples detailing the design of various styles of brick
walls. Adeon is an interesting example of how to provide an interface for
creative work that spans both high-level and low-level concerns.
[18]
Recognizing and using goals in event management
Spotlight on work in progress session 2
/
Smith, Dustin Arthur
/
Lieberman, Henry
Proceedings of ACM CHI 2009 Conference on Human Factors in Computing Systems
2009-04-04
v.2
p.4525-4530
Keywords: PIM, calendaring, common sense, event management, user modeling
© Copyright 2009 ACM
Summary: Personal event management involves planning when, where and how events
should occur, making sure the event's prerequisites are satisfied, and
developing contingencies for when things go wrong. Conventional calendar and
project management tools, however, only record and visualize explicit human
decisions regarding event specifics.
We present Event Minder, a calendar program that takes into account the
goals for which the events are scheduled. Users can input descriptions of
events in natural language, mixing high-level objectives, concrete time and
place decisions, and omit "obvious" common sense details. A commonsense
knowledge base provides sensible defaults, and machine learning refines these
defaults with experience. We can make recommendations for alternative plans,
including alternatives that satisfy higher-level goals in different ways as
well as those that meet immediate constraints. Our current system covers
dining-related events, integrating commonsense with domain knowledge about
specific restaurants, bars and hotels.
[19]
An interface for targeted collection of common sense knowledge using a
mixture model
Information & knowledge management
/
Speer, Robert
/
Krishnamurthy, Jayant
/
Havasi, Catherine
/
Smith, Dustin
/
Lieberman, Henry
/
Arnold, Kenneth
Proceedings of the 2009 International Conference on Intelligent User
Interfaces
2009-02-08
p.137-146
Keywords: common sense reasoning, hierarchical bayes model, human computation,
knowledge acquisition
© Copyright 2009 ACM
Summary: We present a game-based interface for acquiring common sense knowledge. In
addition to being interactive and entertaining, our interface guides the
knowledge acquisition process to learn about the most salient characteristics
of a particular concept. We use statistical classification methods to discover
the most informative characteristics in the Open Mind Common Sense knowledge
base, and use these characteristics to play a game of 20 Questions with the
user. Our interface also allows users to enter knowledge more quickly than a
more traditional knowledge-acquisition interface. An evaluation showed that
users enjoyed the game and that it increased the speed of knowledge
acquisition.
[20]
CSIUI 2009: story understanding and generation for aware and interactive
interface design
Workshops
/
Havasi, Catherine
/
Lieberman, Henry
/
Mueller, Erik T.
Proceedings of the 2009 International Conference on Intelligent User
Interfaces
2009-02-08
p.491-492
Keywords: common sense reasoning, events, intelligent user interfaces, knowledge
collection, story understanding
© Copyright 2009 ACM
Summary: In order to be helpful to people, the intelligent interfaces of the future
will have to acquire, represent, and infer simple knowledge about everyday life
and activities. While much work in AI has represented this knowledge at the
word, sentence, and logical assertion level, we see a growing need to
understand it at a larger granularity, that of stories.
The workshop, like its predecessors, had the goal of bringing together
researchers in common sense reasoning with researchers in intelligent
interfaces. Each year our workshop has a different focus in addition to these
two areas and this year's workshop focused on the acquisition, understanding
and creation of stories.
[21]
Common sense assistant for writing stories that teach social skills
Works in progress
/
Kim, Kyunghee
/
Picard, Rosalind W.
/
Lieberman, Henry
Proceedings of ACM CHI 2008 Conference on Human Factors in Computing Systems
2008-04-05
v.2
p.2805-2810
© Copyright 2008 ACM
Summary: People on the autistic spectrum often have difficulties with social
interaction, and these difficulties are compounded when a person faces the
uncertainty of not knowing what to expect in a new social setting. Detailed,
step-by-step explanations of people's intentions and plausible actions can
often help autistic people make sense of the situation, adapt to the social
rules, and reduce stress associated with the social encounter. Carol Gray's
Social Stories? are carefully structured stories designed to prepare autistic
people for everyday situations such as smiling at friends, waiting in a line,
and staying calm in an audience when the speaker's slides don't match the
handouts. Teachers or parents writing these stories often forget to include
explanations of simple, "common sense" facts and simple variations of the story
that might occur in different circumstances. We present a new tool that helps
the writer explain salient points and think of more variations of the story. It
uses a knowledge base of Common Sense sentences, Open Mind Common Sense, and
inference in a semantic network, ConceptNet. We are investigating whether this
new tool's suggestions are useful by examining how often the writers choose and
use the suggestions that it generates.
[22]
EDITED BOOK
HCI Remixed: Reflections on Works that have Influenced the HCI Community
/
Erickson, Thomas
/
McDonald, David W.
2008
p.337
Cambridge, Massachusetts
MIT Press
Section I - Big Ideas
1. My Vision Isn't My Vision: Making a Career Out of Getting Back to Where I Started
+ Buxton, William
2. Deeply Intertwingled: The Unexpected Legacy of Ted Nelson's Computer Lib/Dream Machines
+ Russell, Daniel M.
3. Man-Computer Symbiosis
+ Baecker, Ronald M.
4. Drawing on SketchPad: Reflections on Computer Science and HCI
+ Konstan, Joseph A.
5. The Mouse, the Demo and the Big Idea
+ Ju, Wendy
Section II - Influential Systems
6. A Creative Programming Environment
+ Lieberman, Henry
7. Fundamentals in HCI: Learning the Value of Consistency and User Models
+ Bly, Sara
8. It is still a Star
+ Bødker, Susanne
9. The Disappearing Computer
+ Streitz, Norbert A.
10. It Really Is All About Location!
+ Dey, Anind K.
Section III - Large Groups, Loosely Joined
11. Network Nation: Human Communication via Computer
+ Kiesler, Sara
12. On the Diffusion of Innovations in HCI
+ Fisher, Danyel
13. From Smart to Ordinary
+ Brown, Barry
14. Knowing the Particulars
+ Erickson, Thomas
15. Back to Samba School: Revisiting Seymour Papert's Ideas on Community, Culture, Computers and Learning
+ Bruckman, Amy
16. The Work to Make Software Work
+ Grinter, Rebecca E.
Section IV - Groups in the Wild
17. McGrath and the Behaviors of Groups (BOGs)
+ Grudin, Jonathan
18. Observing Collaboration: Group-Centered Design
+ Greenberg, Saul
19. Infrastructure and its Effect on the Interface
+ Edwards, W. Keith
20. Taking Articulation Work in CSCW Seriously
+ Fitzpatrick, Geraldine
21. Let's Shack Up: Getting Serious about GIM
+ McDonald, David W.
22. A CSCW Sampler
+ Palen, Leysia
23. Video, Toys, and Beyond Being There
+ Smith, Brian K
Section V - Reflective Practitioners
24. A Simulated Listening Typewriter: John Gould plays Wizard of Oz
+ Schmandt, Chris
25. Seeing the Hole In Space
+ Harrison, Steve
26. Edward Tufte's 1+1=3
+ Jenson, Scott
27. Typographic Space: A Fusion of Design and Technology
+ Forlizzi, Jodi
28. Making Sense of Sense Making
+ Whittaker, Steve
29. Does Voice Coordination Have to be 'Rocket Science'?
+ Aoki, Paul M.
30. Decomposing a Design Space
+ Resnick, Paul
Section VI - There's More to Design
31. Discovering America
+ Winograd, Terry
32. Interaction Design Considered as a Craft
+ Löwgren, Jonas
33. Designing 'Up' in the Software Industry
+ Cherny, Lynn
34. Revisiting an Ethnocritical Approach to HCI: Verbal Privilege and Translation
+ Muller, Michael J.
35. Some Experience! Some Evolution!
+ Cockton, Gilbert
36. Mumford Re-Visited
+ Dray, Susan M.
Section VII - Tacking and Jibbing
37. Learning from Learning from Notes
+ Olson, Judith S.
38. A Site for SOAR Eyes: (Re)placing Cognition
+ Churchill, Elizabeth F.
39. You Can Go Home Again: Revisiting a Study of Domestic Computing
+ Woodruff, Allison
40. From Gaia to HCI: On Multi-disciplinary Design and Co-adaptation
+ Mackay, Wendy E.
41. Fun at Work: Managing HCI with the Peopleware Perspective
+ Thomas, John C.
42. Learning from Engineering Research
+ Newman, William
43. Interaction is the Future of Computing
+ Beaudouin-Lafon, Michel
Section VIII - Seeking Common Ground
44. A Source of Stimulation: Gibson's Account of the Environment
+ Gaver, William
45. When the External Entered HCI: Designing Effective Representations
+ Rogers, Yvonne
46. The Essential Role of Mental Models in HCI: Card, Moran and Newell
+ Ehrlich, Kate
47. A Most Fitting Law
+ Olson, Gary M.
48. Reflections on Card, English, and Burr
+ MacKenzie, I. Scott
49. The Contribution of the Language-Action Perspective to a New Foundation for Design
+ De Michelis, Giorgio
50. Following Procedures: A Detective Story
+ Henderson, Austin
51. Play, Flex, and Slop: Sociality and Intentionality
+ Dourish, Paul
[23]
A Common Sense-Based On-Line Assistant for Training Employees
Intelligent User Interfaces
/
Silva, Júnia Coutinho Anacleto
/
Godoi, Muriel de Souza
/
de Carvalho, Aparecido Fabiano Pinatti
/
Lieberman, Henry
Proceedings of IFIP INTERACT'07: Human-Computer Interaction
2007-09-10
v.1
p.243-254
Keywords: Distance learning; common sense; on-line assistant; training; education;
cognitive strategies; metaphors and analogies
© Copyright 2007 IFIP
Summary: We present a prototype of an on-line assistant to support a training course
about workspace safety issues. The application uses a common sense reasoning
engine and the Brazilian Open Mind common sense knowledge base, to make
inferences about concepts that might be unfamiliar to the students. We explore
the use of metaphors and analogies to explain topics, enhancing learning by
using similarities to help students associate related topics. We believe that
common sense can be used to take into account cultural considerations while
helping learners to build analogies. A survey of students showed that they
considered analogies useful in the learning process, that the system was
helpful in understanding new concepts, and that it helped connect the
information searched for with common sense knowledge.
[24]
Common sense and intelligent user interfaces
Workshops
/
Havasi, Catherine
/
Lieberman, Henry
Proceedings of the 2007 International Conference on Intelligent User
Interfaces
2007-01-28
p.7
© Copyright 2007 ACM
Summary: There is a mutually beneficial relationship between user interfaces and
common sense reasoning and acquisition. Common sense knowledge enables
interfaces to better understand and to be more grounded in the world of the
user, thus improving the user's overall experience with the interface. This
would not be possible without large sources of common sense knowledge, which
likewise benefit from intelligent interfaces designed to make the knowledge
acquisition processes more productive and enjoyable for the contributor. These
two complementary interface types and their interaction are explored in this
workshop.
[25]
What am I gonna wear?: scenario-oriented recommendation
Short papers
/
Shen, Edward
/
Lieberman, Henry
/
Lam, Francis
Proceedings of the 2007 International Conference on Intelligent User
Interfaces
2007-01-28
p.365-368
© Copyright 2007 ACM
Summary: Electronic Commerce on the Web is thriving, but consumers still have trouble
finding products that will meet their needs and desires. AI has offered many
kinds of Recommender Systems [11], but they are all oriented toward searching
based on concrete attributes of the product (e.g. price, color) or the user (as
in Collaborative Filtering). Based on commonsense reasoning technology, we
introduce a novel recommendation technique, Scenario-Oriented Recommendation,
which helps users by mapping their daily scenarios to product attributes, and
works even when users don't know exactly what products they are looking for.
