“I had the privilege to work with Ed for 5 years at Google, first three years of which as collaborators and later reporting to him. Ed is an authoritative leading researcher in the field of HCI, human computation and ML inside and outside Google. Ed has been enlightening people and impacting products using his vision. In addition to an inspiring mentor, he is a great manager. Ed is a master at discovering his team members' strength and utilize them in project matching. His energy, passion, vision and charastics has consistently influenced his team and people around him.”
About
Ed H. Chi (紀懷新) is a Distinguished Scientist (* Sr. Director-level) at Google, leading…
Activity
-
On behalf of Fellows Fund and the Fellow community, I am thrilled to announce our new General Partner, Dr. Jianchang (JC) Mao. Over the past two…
On behalf of Fellows Fund and the Fellow community, I am thrilled to announce our new General Partner, Dr. Jianchang (JC) Mao. Over the past two…
Liked by Ed H. Chi
-
Thanks, Alex Ren. Having spent three decades in major tech companies, I am captivated by the dynamic AI startup ecosystem. I am eager to leverage my…
Thanks, Alex Ren. Having spent three decades in major tech companies, I am captivated by the dynamic AI startup ecosystem. I am eager to leverage my…
Liked by Ed H. Chi
-
Today marks my last day at Microsoft. 15 years ago I interned at Microsoft Research for the first time. 13 years ago I received MSR PhD Fellowship…
Today marks my last day at Microsoft. 15 years ago I interned at Microsoft Research for the first time. 13 years ago I received MSR PhD Fellowship…
Liked by Ed H. Chi
Experience
Education
Volunteer Experience
-
Photographer
Team-M Taekwondo
- Present 3 years 4 months
Education
I volunteer as the team photographer at national and regional events.
Publications
-
Got Many Labels? Deriving Topic Labels from Multiple Sources for Social Media Posts using Crowdsourcing and Ensemble Learning
International World Wide Web Conference (WWW)
Online search and item recommendation systems are often based on being able to correctly label items with topical keywords. Typically, topical labelers analyze the main text associated with the item, but social media posts are often multimedia in nature and contain contents beyond the main text. Topic labeling for social media posts is therefore an important open problem for supporting effective social media search and recommendation. In this work, we present a novel solution to this problem…
Online search and item recommendation systems are often based on being able to correctly label items with topical keywords. Typically, topical labelers analyze the main text associated with the item, but social media posts are often multimedia in nature and contain contents beyond the main text. Topic labeling for social media posts is therefore an important open problem for supporting effective social media search and recommendation. In this work, we present a novel solution to this problem for Google+ posts, in which we integrated a number of different entity extractors and annotators, each responsible for a part of the post (e.g. text body, embedded picture, video, or web link). To account for the varying quality of different annotator outputs, we first utilized crowdsourcing to measure the accuracy of individual entity annotators, and then used supervised machine learning to combine different entity annotators based on their relative accuracy. Evaluating using a ground truth data set, we found that our approach substantially outperforms topic labels obtained from the main text, as well as naive combinations of the individual annotators. By accurately applying topic labels according to their relevance to social media posts, the results enables better search and item recommendation.
-
Swipe vs. scroll: web page switching on mobile browsers
ACM Press
Tabbed web browsing interfaces enable users to multi-task and easily switch between open web pages. However, tabbed browsing is difficult for mobile web browsers due to the limited screen space and the reduced precision of touch. We present an experiment comparing Safari's pages-based switching interface using horizontal swiping gestures with the stacked cards-based switching interface using vertical scrolling gestures, introduced by Chrome. The results of our experiment show that cards-based…
Tabbed web browsing interfaces enable users to multi-task and easily switch between open web pages. However, tabbed browsing is difficult for mobile web browsers due to the limited screen space and the reduced precision of touch. We present an experiment comparing Safari's pages-based switching interface using horizontal swiping gestures with the stacked cards-based switching interface using vertical scrolling gestures, introduced by Chrome. The results of our experiment show that cards-based switching interface allows for faster switching and is less frustrating, with no significant effect on error rates. We generalize these findings, and provide design implications for mobile information spaces.
Other authorsSee publication -
Instant Foodie: Predicting Expert Ratings From Grassroots
CIKM'13
Consumer review sites and recommender systems typically rely on a large volume of user-contributed ratings, which makes rating acquisition an essential component in the design of such systems. User ratings are then summarized to provide an aggregate score representing a popular evaluation of an item. An inherent problem in such summarization is potential bias due to raters’ self-selection and heterogeneity in terms of experiences, tastes and rating scale interpretations. There are two major…
Consumer review sites and recommender systems typically rely on a large volume of user-contributed ratings, which makes rating acquisition an essential component in the design of such systems. User ratings are then summarized to provide an aggregate score representing a popular evaluation of an item. An inherent problem in such summarization is potential bias due to raters’ self-selection and heterogeneity in terms of experiences, tastes and rating scale interpretations. There are two major approaches to collecting ratings, which have different advantages and disadvantages. One is to allow a large number of volunteers to choose and rate items directly (a method employed by e.g. Yelp and Google Places). Alternatively, a panel of raters may be maintained and invited to rate a predefined set of items at regular intervals (such as in Zagat Survey). The latter approach arguably results in more consistent reviews and reduced selection bias, however, at the expense of much smaller coverage (fewer rated items). In this paper, we examine the two different approaches to collecting user ratings of restaurants and explore the question of whether it is possible to reconcile them. Specifically, we study the problem of inferring the more calibrated Zagat Survey ratings (which we dub “expert ratings”) from the user-contributed ratings (“grassroots”) in Google Places. To achieve this, we employ latent factor models and provide a probabilistic treatment of the ordinal ratings. We can predict Zagat Survey ratings accurately from ad hoc user-generated ratings by employing joint optimization. Furthermore, the resulting model show that users become more discerning as they submit more ratings. We also describe an approach towards cross-city recommendations, answering questions such as “What is the equivalent of the Per Se restaurant in Chicago?”
Other authorsSee publication -
Talking in Circles: Selective Sharing in Google+
CHI 2012 (ACM Conference on Human Factors in Computing Systems
Online social networks have become indispensable tools for information sharing, but existing "all-or-nothing" models for sharing have made it difficult for users to target information to specific parts of their networks. In this paper, we study Google+, which enables users to selectively share content with specific "Circles" of people. Through a combination of log analysis with surveys and interviews, we investigate how active users organize and select audiences for shared content. We find that…
Online social networks have become indispensable tools for information sharing, but existing "all-or-nothing" models for sharing have made it difficult for users to target information to specific parts of their networks. In this paper, we study Google+, which enables users to selectively share content with specific "Circles" of people. Through a combination of log analysis with surveys and interviews, we investigate how active users organize and select audiences for shared content. We find that these users frequently engaged in selective sharing, creating circles to manage content across particular life facets, ties of varying strength, and interest-based groups. Motivations to share spanned personal and informational reasons, and users frequently weighed "limiting" factors (e.g. privacy, relevance, and social norms) against the desire to reach a large audience. Our work identifies implications for the design of selective sharing mechanisms in social networks.
-
Who is Authoritative? Understanding Reputation Mechanisms in Quora.
Proceedings of Collective Intelligence 2012
-
Tweets from Justin Bieber’s Heart: The Dynamics of the “Location” Field in User Profiles
ACM SIGCHI 2011
Little research exists on one of the most common, oldest, and most utilized forms of online social geographic information: the 'location' field found in most virtual community user profiles. We performed the first in-depth study of user behavior with regard to the location field in Twitter user profiles. We found that 34% of users did not provide real location information, frequently incorporating fake locations or sarcastic comments that can fool traditional geographic information tools. When…
Little research exists on one of the most common, oldest, and most utilized forms of online social geographic information: the 'location' field found in most virtual community user profiles. We performed the first in-depth study of user behavior with regard to the location field in Twitter user profiles. We found that 34% of users did not provide real location information, frequently incorporating fake locations or sarcastic comments that can fool traditional geographic information tools. When users did input their location, they almost never specified it at a scale any more detailed than their city. In order to determine whether or not natural user behaviors have a real effect on the 'locatability' of users, we performed a simple machine learning experiment to determine whether we can identify a user's location by only looking at what that user tweets. We found that a user's country and state can in fact be determined easily with decent accuracy, indicating that users implicitly reveal location information, with or without realizing it. Implications for location-based services and privacy are discussed.
Other authorsSee publication -
VisualWikiCurator: Human and Machine Intelligence for Organizing Wiki Content
IUI 2011
Corporate wikis are affected by poor adoption rates. The
high interaction costs required to organize and maintain
information in these wikis are a key factor that limits
broader adoption. We present VisualWikiCurator, a wiki
extension designed to lower such costs by (a)
recommending new content to easily update a wiki page,
and (b) extracting structured data from the wiki page while
providing new alternative visualizations of the data. The
visualizations of…Corporate wikis are affected by poor adoption rates. The
high interaction costs required to organize and maintain
information in these wikis are a key factor that limits
broader adoption. We present VisualWikiCurator, a wiki
extension designed to lower such costs by (a)
recommending new content to easily update a wiki page,
and (b) extracting structured data from the wiki page while
providing new alternative visualizations of the data. The
visualizations of extracted semantic data act both as
alternative views and as tools to organize the page content.
Since no information extraction algorithm is perfect with
generic unstructured data, we use a mixed-initiative
approach to allow users to refine machine-extracted
metadata and easily re-organize the content in wiki pages.Other authorsSee publication -
Is Twitter a Good Place for Asking Questions?
Proceedings of the AAAI International Conference on Weblogs and Social Media, Barcelona, Spain. (ICWSM ’11)
-
Want to be retweeted? large scale analytics on factors impacting retweet in twitter network
Proc. of IEEE SocialCom 2010
-
Short and tweet: experiments on recommending content from information streams
Proc. of the 28th International Conference on Human Factors in Computing Systems (CHI2010)
-
An Elaborated Model of Social Search
Information Processing and Management, 46(6)
-
Activity-Based Serendipitous Recommendations with the Magitti Mobile Leisure Guide
ACM Conference on Computer-Human Interaction
This paper presents a context-aware mobile recommender system, codenamed Magitti. Magitti is unique in that it infers user activity from context and patterns of user behavior and, without its user having to issue a query, automatically generates recommendations for content matching. Extensive field studies of leisure time practices in an urban setting (Tokyo) motivated the idea, shaped the details of its design and provided data describing typical behavior patterns. The paper describes the…
This paper presents a context-aware mobile recommender system, codenamed Magitti. Magitti is unique in that it infers user activity from context and patterns of user behavior and, without its user having to issue a query, automatically generates recommendations for content matching. Extensive field studies of leisure time practices in an urban setting (Tokyo) motivated the idea, shaped the details of its design and provided data describing typical behavior patterns. The paper describes the fieldwork, user interface, system components and functionality, and an evaluation of the Magitti prototype.
Other authorsSee publication -
Crowdsourcing user studies with Mechanical Turk
Proceedings of the SIGCHI conference on human factors in computing systems
-
Towards a Model of Understanding Social Search
In Proc. of Computer-Supported Cooperative Work (CSCW'08), ACM Press, pp. 485-494
-
He says, she says: conflict and coordination in Wikipedia
Proceedings of the SIGCHI conference on Human factors in computing systems
-
Power of the few vs. wisdom of the crowd: Wikipedia and the rise of the bourgeoisie
alt.CHI at ACM SIGCHI Conference 2007
-
ScentHighlights: Highlighting Conceptually-Related Sentences During Reading
Proc. Intelligent User Interfaces (IUI), pages 272-274
-
ScentTrails: Integrating browsing and searching on the Web
ACM Transactions on Computer-Human Interaction (TOCHI)
-
LumberJack: Intelligent Discovery and Analysis of Web User Traffic Composition
Proc. ACM-SIGKDD Workshop on Web Mining for Usage Patterns and User Profiles (WebKDD 2002)
Web Usage Mining enables new understanding of user goals on the Web. This understanding has broad applications, and traditional mining techniques such as association rules have been used in business applications. We have developed an automated method to directly infer the major groupings of user traffic on a Web site [Heer01]. We do this by utilizing multiple data features in a clustering analysis. We have performed an extensive, systematic evaluation of the proposed approach, and have…
Web Usage Mining enables new understanding of user goals on the Web. This understanding has broad applications, and traditional mining techniques such as association rules have been used in business applications. We have developed an automated method to directly infer the major groupings of user traffic on a Web site [Heer01]. We do this by utilizing multiple data features in a clustering analysis. We have performed an extensive, systematic evaluation of the proposed approach, and have discovered that certain clustering schemes can achieve categorization accuracies as high as 99% [Heer02b]. In this paper, we describe the further development of this work into a prototype service called LumberJack, a push-button analysis system that is both more automated and accurate than past systems.
-
Using information scent to model user information needs and actions and the Web
Proc. of ACM CHI 2001 Conference on Human Factors in Computing Systems
-
A taxonomy of visualization techniques using the data state reference model
IEEE Symposium on Information Visualization
-
Visualizing the evolution of Web ecologies
CHI1998
Several visualizations have emerged which attempt to
visualize all or part of the World Wide Web. Those
visualizations, however, fail to present the dynamically
changing ecology of users and documents on the Web. We
present new techniques for Web Ecology and Evolution
Visualization (WEEV). Disk Trees represent a discrete
time slice of the Web ecology. A collection of Disk Trees
forms a Time Tube, representing the evolution of the Web
over longer periods of time. These…Several visualizations have emerged which attempt to
visualize all or part of the World Wide Web. Those
visualizations, however, fail to present the dynamically
changing ecology of users and documents on the Web. We
present new techniques for Web Ecology and Evolution
Visualization (WEEV). Disk Trees represent a discrete
time slice of the Web ecology. A collection of Disk Trees
forms a Time Tube, representing the evolution of the Web
over longer periods of time. These visualizations are
intended to aid authors and webmasters with the
production and organization of content, assist Web surfers
making sense of information, and help researchers
understand the Web.Other authorsSee publication
Patents
-
System and method for identifying users relevant to a topic of interest
Issued US US8275769 B1
A system and method for identifying users relevant to a topic of interest is provided. A query comprising one or more topics is executed against a corpus of messages. Voting users associated with the messages matching the query are identified. A set of candidate users comprising users connected to the voting users is generated. A relevancy score is computed for each candidate user. The candidate users are ranked by their respective relevancy score.
Other inventorsSee patent -
Method and system to predict future goal-oriented activity
Issued US 7882056
One embodiment of the present invention provides a method for recommending activities to a user. During operation, the system determines an activity-type distribution based on the user's personal profile and/or population prior information, thereby facilitating prediction of future activities for the user. The system further searches for and receives one or more activities based on the activity-type distribution. The system then scores each received activity and recommends a number of…
One embodiment of the present invention provides a method for recommending activities to a user. During operation, the system determines an activity-type distribution based on the user's personal profile and/or population prior information, thereby facilitating prediction of future activities for the user. The system further searches for and receives one or more activities based on the activity-type distribution. The system then scores each received activity and recommends a number of activities to be performed by the user in the future and a number of corresponding venues, based on the activity-type distribution and the weight distribution.
Other inventorsSee patent -
System and method for supporting targeted sharing and early curation of information
Issued US 8380743
A system and method for supporting targeted sharing and early curation of information is provided. A digital data item selection by a user within a personal information management client is identified. One or more documents in a shared information repository similar to the digital data item are recommended including selecting recommendation criteria. The recommendation criteria are applied to the digital data item and the one or more documents. The one or more documents satisfying the…
A system and method for supporting targeted sharing and early curation of information is provided. A digital data item selection by a user within a personal information management client is identified. One or more documents in a shared information repository similar to the digital data item are recommended including selecting recommendation criteria. The recommendation criteria are applied to the digital data item and the one or more documents. The one or more documents satisfying the recommendation criteria are identified as the similar documents. The similar documents are displayed visually proximate to the digital data item in the personal information client. A selection of one of the similar documents is received and the selected similar document in the shared information repository is updated with the digital data item.
Other inventorsSee patent -
Systems and methods for annotating pages of a 3D electronic document
Issued US
To annotate a three-dimensional electronic object, e.g., document, a user specifies, on a two-dimensional screen, a portion of a page of a three-dimensional document as a specified page area to be annotated by making a stroke. The annotation may be displayed to the user by a hybrid technique where the annotation is displayed by a 3D polyline segment placed behind the near clipping plane of a virtual camera frustrum. At the same time, previous annotations are displayed by another technique, such…
To annotate a three-dimensional electronic object, e.g., document, a user specifies, on a two-dimensional screen, a portion of a page of a three-dimensional document as a specified page area to be annotated by making a stroke. The annotation may be displayed to the user by a hybrid technique where the annotation is displayed by a 3D polyline segment placed behind the near clipping plane of a virtual camera frustrum. At the same time, previous annotations are displayed by another technique, such as, for example, the texture coloring technique. During the intermittent time between the stroke and another stroke the 3D polyline segment is removed from behind the near clipping plane and the page texture is updated with the annotation data. The display techniques support highlighting annotations, free-form annotations, and text annotations.
-
System and method for searching annotated document collections
Issued US 8166056
Projects
-
Magitti Context Aware Leisure Guide
Project Lead. Two phase project do uncover an opportunity for advanced rich media system (broad scope) that would take publishing far beyond print in Japan. Phase one was initial fieldwork in Japan and opportunity brainstorming. Phase two was additional fieldwork and solution brainstorm, followed by advanced prototype development, resulting in the Magitti context-aware leisure guide prototype system, delivered to client in 2006.
Other creators -
Mail2Wiki
-
Mail2Wiki. Corporate wikis are affected by poor adoption rates. The high interaction costs required to share, organize and maintain information on current wikis are limiting broader adoption. To address this problem our research team at PARC (with our colleagues at XRCE) has buit two research prototypes.
(1) An email plugin (MS Outlook) that allows knowledge workers to easily feed new content into their wiki sites directly from the email client (see Hanarahan et al. 2011).
…Mail2Wiki. Corporate wikis are affected by poor adoption rates. The high interaction costs required to share, organize and maintain information on current wikis are limiting broader adoption. To address this problem our research team at PARC (with our colleagues at XRCE) has buit two research prototypes.
(1) An email plugin (MS Outlook) that allows knowledge workers to easily feed new content into their wiki sites directly from the email client (see Hanarahan et al. 2011).
(2) A a wiki plugin (MediaWiki) that allows wiki curators to update and organize the content shared on the wikis via a combination of machine-based functions and human input on interactive visualizations (see Kong et al. 2011).Other creatorsSee project -
Mail2Tag
-
I worked on the design and evaluation of Mail2Tag with Ed Chi, Les Nelson, and Rowan Nairn. Mail2Tag is a corporate blog developed and deployed at PARC. It supports sharing directly via email: workers define and use tagging keywords as email addresses. It supports lightweight collaboration and builds on current email practices in the enterprise. Also, it makes the routing of information across the organization smarter (less noisy) via recommendation functions.
Other creatorsSee project
Languages
-
Mandarin
Native or bilingual proficiency
-
Cantonese
Professional working proficiency
-
English
Native or bilingual proficiency
Recommendations received
11 people have recommended Ed H.
Join now to viewMore activity by Ed H.
-
Big news from me today – I’m joining LinkedIn as the new Chief Information Security Officer! I’m so excited to join LinkedIn and build great things…
Big news from me today – I’m joining LinkedIn as the new Chief Information Security Officer! I’m so excited to join LinkedIn and build great things…
Liked by Ed H. Chi
-
✨ Excited to be in #Barcelona for the #KDD2024 Conference, representing #ExpediaGroup. Loved the workshop yesterday on #GenAI for Recommendation…
✨ Excited to be in #Barcelona for the #KDD2024 Conference, representing #ExpediaGroup. Loved the workshop yesterday on #GenAI for Recommendation…
Liked by Ed H. Chi
-
We are excited to host our second workshop on two-sided marketplace optimization (TSMO 2024) at #KDD2024 in Barcelona on Monday, August 26th 2024…
We are excited to host our second workshop on two-sided marketplace optimization (TSMO 2024) at #KDD2024 in Barcelona on Monday, August 26th 2024…
Liked by Ed H. Chi
-
Back in the Bay Area in September & Ready to chat about new opportunities After an incredible 18-month sabbatical exploring the world, my wife and I…
Back in the Bay Area in September & Ready to chat about new opportunities After an incredible 18-month sabbatical exploring the world, my wife and I…
Liked by Ed H. Chi
-
After almost 2 decades, I am moving on from Google. Working with the incredible teams at Google has been a highlight of my career. I will always…
After almost 2 decades, I am moving on from Google. Working with the incredible teams at Google has been a highlight of my career. I will always…
Liked by Ed H. Chi
-
Hello from [ICML] Int'l Conference on Machine Learning in Vienna! 🇦🇹 At our booth, we’re hosting live research demos on Gemini Nano, LearnLM - our…
Hello from [ICML] Int'l Conference on Machine Learning in Vienna! 🇦🇹 At our booth, we’re hosting live research demos on Gemini Nano, LearnLM - our…
Liked by Ed H. Chi
-
You can now access 1.5 Flash in Gemini. ⚡ Optimized for speed and efficiency, it comes with a 32K context window - meaning you can ask more complex…
You can now access 1.5 Flash in Gemini. ⚡ Optimized for speed and efficiency, it comes with a 32K context window - meaning you can ask more complex…
Liked by Ed H. Chi
-
Thrilled to announce this new partnership which will double the number of AI research placement opportunities offered through the Google DeepMind…
Thrilled to announce this new partnership which will double the number of AI research placement opportunities offered through the Google DeepMind…
Liked by Ed H. Chi
-
🌟 Exciting Day 1 at the Wu Ta-You Science Camp 🌟 I am honored to participate in the 2024 Wu Ta-You Science Camp, focused on "The Impact of AI –…
🌟 Exciting Day 1 at the Wu Ta-You Science Camp 🌟 I am honored to participate in the 2024 Wu Ta-You Science Camp, focused on "The Impact of AI –…
Liked by Ed H. Chi
-
As a #womanintech and a member of #WomenatGoogleTaiwan, I'm honored to host the annual TechWomen@TW event at our newly opened campus in…
As a #womanintech and a member of #WomenatGoogleTaiwan, I'm honored to host the annual TechWomen@TW event at our newly opened campus in…
Liked by Ed H. Chi
-
Dear colleagues, we would like to invite you to submit contributions to the main track of WSDM 2025, the 18th edition of the ACM International…
Dear colleagues, we would like to invite you to submit contributions to the main track of WSDM 2025, the 18th edition of the ACM International…
Liked by Ed H. Chi
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More