Dr. Pearl Pu

Background

Short Biography

Dr. Pearl Pu currently leads the HCI Group in the School of Computer and Communication Sciences at the Swiss Federal Institute of Technology in Lausanne (EPFL). Her research interests include recommendation technology, electronic commerce, user adoption of technology, online consumer decision behavior, decision support, content-based product search, travel planning tools, trust-inspiring interfaces for recommender agent, music recommenders, scalable user experience, and social web.

A native from Shanghai, China, she moved to the United States shortly after passing the entrance examination to the ZheJiang University (currently ranked top three in Computer Science in China). She obtained her Master and Ph.D. degrees from the University of Pennsylvania in artificial intelligence and computer graphics. She was a visiting scholar at Stanford University in 2001, both in the database and HCI groups. While there, she gave seminars at Xerox PARC's weekly seminar series and Stanford's HCI Design Studio class as guest lecturer.

She was also a co-founder of Iconomic Systems (1997-2001), and invented the any-criteria example-based search method for travel solutions. The company was successfully sold to i:FAO, Germany.

Her recent publications included papers from ACM TOCHI, UMUAI, the Journal of Artificial Intelligence Research, the Constraints journal, the Knowledge-Based Systems Journal, AAAI, ACM Recsys, ACM ECommerce, International Conferences on Intelligent User Interface, ACM CHI, IEEE InfoVis, and AVI.

Education

Ph.D. in Computer and Information Sciences. University of Pennsylvania, Philadelphia, U.S.A.
M.S.E. in Computer and Information Sciences. University of Pennsylvania, Philadelphia, U.S.A.
B.S. in Computer Science and Mathematics. Queens College, The City University of New York, U.S.A.

Employment

Senior Scientist (Maitre d'enseignement et de recherche), School of Computer and Communication Sciences, EPFL, Switzerland. 2008.
Research Scientist and lecturer (chargée de cours), School of Computer and Communication Sciences, EPFL, Switzerland. 2000 - 2007.
Visiting Scholar, Stanford University, California, USA. January 2001 - June 2001.
Research Scientist and lecturer (chargée de cours), Microengineering Department, EPFL, Switzerland. 1993 - 2000.
Visiting Professor, Artificial Intelligence Laboratory, Computer Science Department, EPFL, Switzerland. January 1992 - August 1992.
Assistant Professor, University of Connecticut, Department of Computer Science and Engineering. 1988 - 1993

Editorial Positions

Member of the Editorial Board, AI Magazine, from 2012
Associate Editor for ACM Transactions on Interactive Intelligent Systems (TiiS), from 2012
Associate Editor for the IEEE Transactions on Multimedia, 2007-present
Associate Editor for UMUAI, the personalization journal, http://www.umuai.org/, 2009 - present. Impact factor: 3.1 from Thomson ISI.

Service to Scientific Communities

Member of the Steering Commitee for ACM International Conference on Recommender Systems.
Track Chair on Behavioral Analysis and Persoanlization, WWW 2012, April 16-20, Lyon, France.
Area Chair for the International Joint Conference on Artificial Intelligence, July 16-22, 2011, Barcelona, Spain.
General Chair for the ACM Conference on Intelligent User Interfaces, February 13-16, 2011, Palo Alto, California.
Program Co-Chair for the 10th ACM Conference on Electronic Commerce, July 6-10, 2009, Stanford, California.
General Chair for the 2008 ACM International Conference on Recommender Systems, October 23-26, 2008, Lausanne, Switzerland.
Program Co-Chair for the International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems 2008 (AH 2008), July 28- August 1, 2008, Hanover, Germany.
Associate Chair for Short papers at the ACM Conference on Computer/Human Interaction 2007 (CHI07), April 28 - May 3, 2007, San Jose, California.
Program Chair for Short Papers at the ACM Conference on Recommender Systems (RecSys07), October 19-20, 2007, Minneapolis, Minnesota.
Tutorial Chair for the ACM International Conference on Intelligent User Interfaces (IUI07), 2007.
Publicity Chair for the ACM International Conference on Intelligent User Interfaces (IUI07), 2007.
Conference program chair for the IFIP TC2/WG2.6 Sixth Working Conference on Visual Database Systems, 2002.

Research

Interests

My research is multi-disciplinary and focuses on issues in the intersection of human computer interaction, artificial intelligence, and classical and behavioral decision theories. In my earlier work, I considered the interaction of artificial intelligence and visualization techniques in various decision support systems, for example for aircraft allocation and network configuration. Systems based on my work were used at Swissair and Singapore Airlines.

In the last few years, I have focused my attention on preference-based search in online environments: how to help a user find the most preferred item in a large database of multi-attribute structured items. A typical example of preference-based search is finding a preferred item in e-commerce sites such as www.google.com/products, www.shopping.yahoo.com, www.shopping.msn.com, www.kelkoo.fr, etc. Online databases are known as the deep web, believed to be 500 times bigger than the surface web. Most keyword based search engines, such as Yahoo and Google, cannot perform preference-based search.

The main challenge in preference-based search is that while users want high accuracy in finding what they are looking for, their effort in performing this operation is limited. It has been known for some time that the existing tools, such as those used in e-commerce websites do not always allow users to find their most preferred items. I was among the first to show why and how such failures actually occur.

Based on these realizations, I have led a team of researchers to develop a suite of search mechanisms, such as example critiquing, preference-based suggestion, MAUT-based critiquing, and preference-based organization interfaces. Our aim was to develop decision aid tools and interface technologies to motivate and assist users to improve their search accuracy. At the same time, our methods also ensured that users do not expend more effort than what is required by existing tools .

Keywords: preference-based search, e-commerce, preference elicitation, human computer interaction, artificial intelligence, intelligent user interfaces, users’ technology adoption issues in e-commerce, qualitative decision theory, mixed initiative systems, constraint satisfaction problem solving, information visualization, web information systems, intelligent agents, case-based reasoning, multimedia information retrieval.

Main Results

A Mixed Initiative Approach to Online Product Search
Pearl Pu and Boi Faltings. Enriching Buyers' experiences: the SmartClient Approach. In Proceedings of the ACM SIGCHI conference on Human Factors in Computing Systems, pages 289-296, The Hague, April 2000 (acceptance rate 21%).

While pursuing my degrees in computer science, I was also very interested in subjects taught in mathematics and economics departments. In particular, I studied decision theories such as “Theory of Games and Economic Behavior,” by Von Neumann and Morgenstein and later, “Decisions with Multiple Objectives: Preferences and Value Trade-Offs,” by Keeney and Raiffa. However, the opportunity to combine decision theory and computer science did not occur until the late 90s when online stores emerged and e-commerce became a research topic. I saw this as the perfect time to apply some of the results from decision theories to solve emerging computer science problems. More specifically, I began investigating how to help online buyers make sound decisions as they search for products in a large database.
The first step is to model product search as a decision problem where users’ preferences are used to guide the search process to find their most preferred items. In classical decision theories, the assumption is that people are able to articulate their preferences and hence their value functions before solving the decision problem. The online stores in the early days followed this idea and most user interfaces first elicited their preferences as if they were innate to the users. While observing how users interact with such product search tools, I began to realize that humans do not behave that way under those specific circumstances. Humans’ needs and preferences for products cannot be expressed independently of their knowledge of the product space.

At this point, I began thinking about human computer interaction (HCI) problems in a serious way. I realized that there is a fundamental difference between how humans behave and how we model human behaviors in computer science and decision theory. I was among few researchers in AI at that time to start working on interaction methods that address this difference. In this paper, I first challenged the assumption that users are able to articulate their needs before viewing the products and comparing them. Instead, their needs are defined as a result of browsing available products. The products selected by the machine and displayed to the user, therefore, highly determine the formulation and accuracy of the users’ value functions and consequently their choice behavior. I proposed a mixed initiative conversational model that allows users to express their preferences based on example products shown to them, and in ways that they can easily refine them in order to improve their decision quality. With my background in constraint problem solving techniques, my co-author and I also found a unique framework to support this fluid interaction.
This mixed initiative model is eventually known as the example critiquing method for online product search and remains an important work for our group as well other groups in designing interactive decision support systems.

Other Relevant Publications

Pearl Pu, Boi Faltings, and Marc Torrens. Effective Interaction Principles for Online Product Search Environments. In Proceedings of the IEEE/WIC/ACM International Joint Conference on Intelligent Agent Technology and Web Intelligence, pages 724-727, September 20-24, 2004. (Acceptance rate 16%.)

Marc Torrens, Boi Faltings and Pearl Pu. SmartClients: Constraint Satisfaction as a Paradigm for Scaleable Intelligent Information Systems. CONSTRAINTS: an International Journal. Kluwer Academic Publishers. 7 (1), pages 49-69, 2002.

Pearl Pu and Boi Faltings. Decision Tradeoff Using Example Critiquing and Constraint Programming. CONSTRAINTS: an International Journal. Kluwer Academic Publishers. 9 (4), pages 289-310, 2004.

User Experience Research in Online Environments: Helping Users Make Sound Decisions without demanding too Much of Their Effort

Pearl Pu and Li Chen. Integrating Tradeoff Support in Product Search Tools for E-Commerce Sites. In Proceedings of the ACM Conference on Electronic Commerce (EC'05), Vancouver, Canada, pages 269-278, June 5-8, 2005. (Acceptance rate 28%.)

After developing the example critiquing model, I set out to investigate the exact user benefits that our tools are able to deliver. This marked the beginning of my interest in understanding user experience issues in e-commerce. It seemed that for any given tool, there were many directions in which one could observe user benefits and publish some papers about the results. However, not every benefit makes a long-lasting impact on users’ positive experience; in e-commerce research this subject was especially ill defined. I determined that my research would be directed towards long-term user benefits, which would ultimately lead to enhancements that truly aid the user in their quest to make the best available decision.

I realized that the first thing to do is to establish a user experience evaluation framework with which to measure the benefits of product search tools. The second priority is to identify a commonly agreed baseline model.
The logical thing to do at that point was to examine the evaluation criteria used in similar fields such as case-based retrieval and information retrieval to see if they can be adopted in preference-based search. In both case-based and information retrieval, the criteria were established based on an assumption is that there is a pre-defined item the tool must find. Under this framework, we can then use the leave-one out procedure or the precision/recall formalism to measure the accuracy of a tool. However, this is largely a performance measure of a tool. It is not sufficient to characterize user experience. I designed a procedure that can measure a user’s decision accuracy by comparing what he or she finds through the use of a tool versus what she finds after reviewing all items in a database. If a user does not switch to another item after having reviewed all items in a database, then we say that she has accurately found the target item with the help of the tool. Decision accuracy is thus defined as the percentage of users able to find their target choice with the help of a tool.

In addition to decision accuracy, I also proposed to measure the users’ information processing effort in achieving this accuracy. Hence, the notion of relative effort was defined. In this paper, I emphasized that achieving high accuracy without consuming much more effort as the main criteria to evaluate preference-based search tools. This framework was crucial in establishing an agenda for pursuing user experience research in online shopping environments.
After some additional observations, I became aware that there is a third dimension: users’ confidence in their choice measured as the confidence with which they believe they have found the most desired item. Even though users’ decision confidence is a subjective measure and is defined differently from decision accuracy, we found the two parameters to be highly correlated, at least in our experiments. I also identified the ranked list search tool as the baseline to compare with our tools as it was at the time the norm used in many online stores as the main product search engine.

This three-criteria evaluation framework is being recognized as the main user performance evaluation procedure for product search tools and is currently used by other researchers.

Other Relevant Publications

Pearl Pu and Pratyush Kumar. Evaluating Example-based Search Tools. In Proceedings of the ACM Conference on Electronic Commerce (EC'04), pages 208-217, May 17-20, 2004, New York, USA (acceptance rate 16%).

Pearl Pu, Paolo Viappiani and Boi Faltings. Increasing User Decision Accuracy Using Suggestions. In Proceedings of the SIGCHI conference on Human factors in computing systems (CHI'06), Montreal, Canada, pages 121-130, April 22-27, 2006. (Acceptance rate 23%.)

Paolo Viappiani, Boi Faltings, and Pearl Pu. Preference-based search using example-critiquing with suggestions. Journal of Artificial Intelligence Research(JAIR), 27, pages 465-503, 2006.

Li Chen and Pearl Pu. The Evaluation of a Hybrid Critiquing System with Preference-based Recommendations Organization. In Proceedings of ACM Recommender Systems, Minneapolis, Minnesota, USA, October 19-20, 2007 (to appear).

Evaluating Critiquing based Recommender Agents

Li Chen and Pearl Pu. Evaluating Critiquing-based Recommender Agents. In Proceedings of Twenty-first National Conference on Artificial Intelligence (AAAI-06), pages 157-162, Boston, USA, July 16-20, 2006. (Acceptance rate 21%).

A critiquing based recommender agent simulates an artificial salesperson that recommends options based on users’ current preferences and then elicits users’ feedback in the form of critiques such as “I would like something cheaper” or “with faster processor speed.”

In my recent work, I have focused on comparing the strengths and weaknesses of various critiquing based recommender systems. The objective is to identify an evaluative framework for such systems as well as designing hybrid systems that can potentially combine the best of different approaches. In this paper, we started out comparing two well known critiquing based recommender agents: dynamic critiquing and example critiquing systems.

Sometimes after the investigation began, we realized that the difference does not lie as much in the system itself as it lies in the critiquing opportunities that the system presents to the user. We found that there are two main ways a user can perform a critique. In the user-motivated approach, she is able to freely combine both unit and compound critiques while searching for the most preferred product. In the system-proposed approach, the user can only select one of a set of critiques proposed by the system. It seems that in the former case, the user is well in control of deciding which direction she would like to find her target product whereas in the latter, she is only able to choose one proposed by the system. Therefore, we realized that user control is a critical issue to pursue. We designed our experiment so that we were able to see whether users preferred one type of critiquing opportunity over the other and how much of the user control issue was able to influence user experience, such as decision accuracy, user confidence, and users’ relative effort. We found that user-motivated critiques were more frequently applied and the example critiquing system employing only this type of critiques achieved the best results.

Today, in the area of recommender systems, other groups have followed similar practices of using user evaluation as a way to reveal system design features that best influence user experience. See other publications from our group as well as publications from collaboration with other research groups in performing comparative user studies.

Other Relevant Publications

Paolo Viappiani, Boi Faltings and Pearl Pu. Evaluating Preference-based Search Tools: a Tale of Two Approaches. In Proceedings of the Twenty-first National Conference on Artificial Intelligence (AAAI-06), pages 205-210, Boston USA, July 16-20, 2006. (Acceptance rate 21%.)

Li Chen and Pearl Pu. Hybrid Critiquing-based Recommender Systems. In Proceedings of International Conference on Intelligent User Interfaces (IUI2007), pages 22-31, Hawaii, USA, January 28-31, 2007. (Acceptance rate 22%.)

James Reilly, Jiyong Zhang, Lorraine McGinty, Pearl Pu and Barry Smyth. A Comparison of Two Compound Critiquing Systems. In Proceedings of the International Conference on Intelligent User Interfaces(IUI2007) , pages 317-320, Hawaii, USA, January 28-31, 2007. Short paper.

James Reilly, Jiyong Zhang, Lorraine McGinty, Pearl Pu and Barry Smyth. Evaluating Compound Critiquing Recommenders: A Real-User Study. In Proceedings of ACM Conference on Electronic Commerce (EC'07), pages 114-123, San Diego, USA, June 11-15, 2007. (Acceptance rate 27%.)

Li Chen and Pearl Pu. Preference-Based Organization Interface: Aiding User Critiques in Recommender Systems. In Proceedings of International Conference on User Modeling (UM2007), Corfu, Greece, June 25-29, 2007. (Acceptance rate 19.6%.) Best Student Paper Award.

Li Chen and Pearl Pu. The Evaluation of a Hybrid Critiquing System with Preference-based Recommendations Organization. In Proceedings of ACM Recommender Systems, Minneapolis, Minnesota, USA, October 19-20, 2007 (to appear). Short paper.

Seminars

Invited Talks

User Issues in Recommender Systems, Computer Science Department, Tsinghua University and Google Research China, Beijing, China, July 16, 2008.
Recommender Systems, Credit Suisse, Information Technology, CTO Private Banking, Zurich, June 10, 2008.
Towards Human Computer Collaboration, Department of Informatics, University of Zurich, Zurich, May 26, 2008.
Intelligent User Interfaces for Product Search, LAMSADE (Laboratoire d’Analyse et Modélisation de Systèmes pour l’Aide à la décision), Université Paris Dauphine, June 26, 2007.
Preference-based Search: Interaction Design Guidelines, Business School, University of Lausanne, June 12, 2007.
Personal vs. Social Recommender Systems Used in Entertainment Websites, Microsoft Research Asia, Beijing, China, March 2, 2007.
Preference-based Search, GroupLens, Department of Computer Science, University of Minnesota, January 22, 2007.
How E-Commerce Research in the West is Relevant in China, Fudan University, China, November 20, 2006.
How E-Commerce Research in the West is Relevant in China, Tsinghua University, China, November 15, 2006.
Intelligent User Interfaces for Product Search, Asia Institute of Technology (AIT), Bangkok, Thailand, February 6, 2006.
Intelligent User Interfaces for Product Search, Humboldt University Berlin, Germany, October 25, 2005.
Intelligent User Interfaces for Product Search, Hanover University, Germany, October 24, 2005.
Preference Models and Applications, Tutorial given at the International Joint Conference of Artificial Intelligence, Edinburgh , Scotland , July 30, 2005.
Intelligent Interfaces for Preference-Based Search , Tutorial given at the International Conference on Intelligent User Interfaces, San Diego , California , January 9, 2005.
New Search Tools for 2nd Generation E-Commerce, the APWeb (Asia Pacific Web) conference, Hangzhou, China, April 13th, 2004.
New Search Tools for 2nd Generation E-Commerce, Asia Institute of Technology, Bangkok, Thailand, April 8th, 2004.
User-Involved Tradeoff Analysis in Configuration Tasks, Cork Constraint Computation Center, University College Cork, July 17th, 2003.
User-Involved Preference Elicitation in Qualitative Decision Theory, Cork Constraint Computation Center, University College Cork, June 12th, 2003.
User-Involved Preference Elicitation in Qualitative Decision Theory, Beijing University, April 3rd, 2003.
Human Factor Theories from Cognitive and Social Sciences, Tshinghua University, China, April 4th, 2003.
Semantic Fisheye Views --- Microsoft Research Center Asia (Beijing), October 25th, 2002.
Enriching buyers' experiences: the SmartClient Approach ---- Invited colloquium speaker at Xerox's Palo Alto Research Center, Palo Alto, March 6, 2001.
Revolutionize Travel e-commerce sites: some experiences and unsolved issues in information design ---- Invited lecture at Stanford University, Stanford, May 5, 2001.
Interaction Homme-Machine ---- Keynote speaker at Siemens' 150th anniversary, Palais de Beaulieu, Switzerland, May 13, 1997.

Tutorials

Tutorial Speaker, Preference-Based Search, ACM International Conference on Intelligent User Interfaces, 2005
Tutorial Speaker, Preference Models and Applications, International Joint Conference on Artificial Intelligence, 2005.

Publications

Journal articls

Li Chen and Pearl Pu. Preference-based Organization for Suggesting Critiques in Recommender Systems. ACM Transactions on Computer-Human Interaction (TOCHI), to appear in 2009.
Li Chen and Pearl Pu. Interaction Design Guidelines on Critiquing-based Recommender Systems. User Modeling and User-Adapted Interaction Journal (UMUAI), Springer Netherlands, Volume 19, Issue3, Pages 167-206, 2009.
Pearl Pu and Li Chen. User-Involved Preference Elicitation for Product Search and Recommender Systems. AI Magazine 29(4), pp. 93-103, Winter 2008.
Pearl Pu, Li Chen and Pratyush Kumar. Evaluating Product Search and Recommender Systems for E-Commerce Environments. Electronic Commerce Research Journal, 8(1-2), June, pages 1-27, 2008.
Pearl Pu and Li Chen. Trust-Inspiring Explanation Interfaces for Recommender Systems. Journal of Knowledge Based Systems, Elsevier Publishers, Volume 20, Issue 6, Pages 542-556 Auguest 2007.
Paolo Viappiani, Boi Faltings, and Pearl Pu. Preference-based search using example-critiquing with suggestions. Journal of Artificial Intelligence Research(JAIR), 27, pages 465-503, 2006.
Jiyong Zhang and Pearl Pu. Performance Evaluation of Consumer Decision Support Systems. The International Journal of E-Business Research, Idea Group Publishing, 2(3), pages 28-45, 2006.
Paul Janecek and Pearl Pu. An Evaluation of Semantic Fisheye Views for Opportunistic Search in an Annotated Image Collection. Journal of Digital Libraries. Springer-Verlag. 5(1), pages 42-56, 2005.
Pearl Pu and Boi Faltings. Decision Tradeoff Using Example Critiquing and Constraint Programming. CONSTRAINTS: an International Journal. Kluwer Academic Publishers. 9 (4), pages 289-310, 2004.
Boi Faltings, Marc Torrens, and Pearl Pu. Solution Generation with Qualitative Models of Preferences. International Journal of Computational Intelligence and Applications. Blackwell publishing. Volume 20, Number 2, pages 246-264, May, 2004.
Marc Torrens, Boi Faltings and Pearl Pu. SmartClients: Constraint Satisfaction as a Paradigm for Scaleable Intelligent Information Systems. CONSTRAINTS: an International Journal. Kluwer Academic Publishers. 7 (1), pages 49-69, 2002.
P. Pu and G. Melissargos. Visualizing Resource Allocation Tasks. IEEE Computer Graphics and Applications. IEEE Computer Society Press. 17 (4), pages 6-9, July/August 1997.
Boi Faltings and Pearl Pu. Imagery for open-world spatial problems. Computational Intelligence, special issue on Computational Imagery, 9 (4), pages 372-376, November 1993.
Pearl Pu. Simulating Both Dynamic and Kinematic Behaviors of Mechanisms. The International Journal for Artificial Intelligence in Engineering. 6 (3), pages 136-155, July, 1991.
Pearl Pu and Markus Reschberger. Assembly Sequence Planning using Case-Based Reasoning Techniques. Knowledge-Based Systems, Volume 4 No.3, pages 171-187, September 1991.
Pearl Pu. Intelligent CAD Systems: A Synergical Approach of Artificial Intelligence and Engineering. Computational Intelligence: An International Journal. Blackwell publishing. 6 (2), pages 81-90, May 1990.
Alberto Izaguirre, Pearl Pu, and John Summers. A New Development in Camera Calibration: Calibrating a Pair of Mobile Cameras. The International Journal of Robotics Research 6: 104-116, 1987.
Back to top

Edited Books, Book Chapters, Guest Editor to Special Issues

P. Pu, Q. Li, and Xiaofang Zhou (editors). Selected Papers from the Sixth IFIP 2.6 Working Conference on Visual Database Systems. The Journal of the World Wide Web, Kluwer Academic Publishers, May 2003.
Xiaofang Zhou and Pearl Pu (editors). Visual and Multimedia Information Management. Kluwer Academic Publishers, May 2002.
Mary Lou Maher and Pearl Pu (editors). Issues and Applications of Case-based Reasoning for Design, Lawrence Erlbaum Associates, Hillsdale, New Jersey, 1997.
P. Pu and L. Purvis. Formalizing the adaptation Process for Case-based Design. A chapter in Issues and Applications of Case-based Reasoning in Design. Lawrence Erlbaum Associates, New Jersey. Pages 221-240, 1997.
Pearl Pu (guest editor). Issues in Case-Based Design Systems. Artificial Intelligence in Engineering Design, Analysis and Manufacturing (AI EDAM), May 1993.
P. Pu and N.I. Badler. Design Knowledge Capture and Causal Simulation. A chapter in Intelligent CAD Systems, edited by Hiroyuki Yoshikawa and David Gossard, North-Holland, February 1989.
Pearl Pu and Norman I. Badler. Design Knowledge Capturing for Device Behavior Reasoning. A chapter in Artificial Intelligence in Engineering: Design, Computational Mechanics Publications, Southampton, Stanford, CA, pages 37-56, August 1988.
Back to top

Highly Selective Peer-Reviewed Conference Papers

Barry O'Sullivan, Alexandre Papadopoulos, Boi Faltings and Pearl Pu. Representative Explanations for Over-Constrained Problems. In Proceedings of AAAI-2007, July 2007. (Acceptance rate 27%.)
Li Chen and Pearl Pu. Preference-Based Organization Interface: Aiding User Critiques in Recommender Systems. In Proceedings of International Conference on User Modeling (UM2007), Corfu, Greece, June 25-29, 2007. (Acceptance rate 19.6%.) Best Student Paper Award.
James Reilly, Jiyong Zhang, Lorraine McGinty, Pearl Pu and Barry Smyth. Evaluating Compound Critiquing Recommenders: A Real-User Study. In Proceedings of ACM Conference on Electronic Commerce (EC'07), pages 114-123, San Diego, USA, June 11-15, 2007. (Acceptance rate 27%.)
Li Chen and Pearl Pu. Hybrid Critiquing-based Recommender Systems. In Proceedings of International Conference on Intelligent User Interfaces (IUI2007), pages 22-31, Hawaii, USA, January 28-31, 2007. (Acceptance rate 22%.)
Li Chen and Pearl Pu. Evaluating Critiquing-based Recommender Agents. In Proceedings of Twenty-first National Conference on Artificial Intelligence (AAAI-06), pages 157-162, Boston, USA, July 16-20, 2006. (Acceptance rate 21%).
Paolo Viappiani, Boi Faltings and Pearl Pu. Evaluating Preference-based Search Tools: a Tale of Two Approaches. In Proceedings of the Twenty-first National Conference on Artificial Intelligence (AAAI-06), pages 205-210, Boston USA, July 16-20, 2006. (Acceptance rate 21%.)
Jiyong Zhang, Pearl Pu, and Boi Faltings. Agile Decision Agent for Service-Oriented E-Commerce Systems. In Proceedings of The 8th IEEE International Conference on E-Commerce Technology and The 3rd IEEE International Conference on Enterprise Computing, E-Commerce, and E-Services (CEC/EEE'06), pages 182-189, IEEE Computer Society, June 2006. (Acceptance rate 26%.)
Jiyong Zhang and Pearl Pu. A Comparative Study of Compound Critique Generation in Conversational Recommender Systems. In Proceedings of the 4th International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems (AH2006), volume 4018 of Lecture Notes in Computer Science, pages 234-243, Dublin, Ireland, June 2006. Springer. (Acceptance rate 18%.) Best Student Paper Award.
Pearl Pu, Paolo Viappiani and Boi Faltings. Increasing User Decision Accuracy Using Suggestions. In Proceedings of the SIGCHI conference on Human factors in computing systems (CHI'06), Montreal, Canada, pages 121-130, April 22-27, 2006. (Acceptance rate 23%.)
Pearl Pu and Li Chen. Trust Building with Explanation Interfaces. In Proceedings of the 11 the International Conference on Intelligent User Interface (IUI'06), Sydney, Australia, page 93-100, January 29-February 1, 2006. (Acceptance rate 24%.)
Pearl Pu and Li Chen. Integrating Tradeoff Support in Product Search Tools for E-Commerce Sites. In Proceedings of the ACM Conference on Electronic Commerce (EC'05), Vancouver, Canada, pages 269-278, June 5-8, 2005. (Acceptance rate 28%.)
Paul Janecek and Pearl Pu. Opportunistic Search with Semantic Fisheye Views. In Proceedings of The Fifth International Conference on Web Information Systems Engineering (WISE2004), Brisbane, Australia, pages 668--680, November 22-24, 2004. (Acceptance rate 22.7%.).
Pearl Pu, Boi Faltings, and Marc Torrens. Effective Interaction Principles for Online Product Search Environments. In Proceedings of The IEEE/WIC/ACM International Joint Conference on Intelligent Agent Technology and Web Intelligence, pages 724-727, September 20-24, 2004. (Acceptance rate 16%.)
Pearl Pu and Pratyush Kumar. Evaluating Example-based Search Tools. In Proceedings of the ACM Conference on Electronic Commerce (EC'04), pages 208-217, May 17-20, 2004, New York, USA (acceptance rate 16%).
Boi Faltings, Pearl Pu, Marc Torrens, and Paolo Viappiani. Design Example-Critiquing Interaction. In Proceedings of the International Conference on Intelligent User Interface (IUI-2004), ACM Press, pages 22-29, Funchal, Madeira, Portugal, January 2004. (Acceptance rate 28%.)
Paul Janecek and Pearl Pu. A Framework for Designing Fisheye Views to Support Multiple Semantic Contexts. In Proceedings of the International Conference on Advanced Visual Interfaces (AVI '02), ACM Press, pages 51-58, 2002. (Acceptance rate 30%.)
Pearl Pu and Denis Lalanne. Design Visual Thinking Tools for Mixed Initiative Systems. In Proceedings of the International Conference on Intelligent User Interfaces, ACM Press, pages 119-126, 2002. (Acceptance rate 30%.)
Pearl Pu and Denis Lalanne. Interactive Problem Solving Via Algorithm Visualization. In Proceedings of the IEEE Symposium on Information Visualization 2000 (InfoVis 2000), pages 145-154, Salt Lake City, Utah, October 9-10, 2000. (Acceptance rate 26%.)
Pearl Pu and Boi Faltings. Enriching Buyers' experiences: the SmartClient Approach. In Proceedings of the ACM SIGCHI conference on Human Factors in Computing Systems, pages 289-296, The Hagues, April 2000 (acceptance rate 21%).
Pearl Pu and Denis Lalanne. Human and Machine Collaboration in Creative Design. In Proceedings of the European Conference of Artificial Intelligence, Budapest, pages 276-282, August 1996. (Acceptance rate 29%.)
Lisa Purvis and Pearl Pu. Adaptation Using Constraint Satisfaction Techniques. In Proceedings of the International Conference on Case-based Reasoning, Sesimbra, Portugal, pages 289-300, October 1995.
Pearl Pu and Lisa Purvis. Assembly Planning Using Case Adaptation Methods. In Proceedings of the IEEE International Conference on Robotics and Automation, vol 1, pages 982-987, Nagoya, Japan, May 1995.
Pearl Pu and James D. Hughes. Integrating AGV Schedules in a Scheduling System for Flexible Manufacturing Environment. In Proceedings of the 1994 IEEE International Conference on Robotics and Automation, pages 3149-3154, May 8-3, 1994, San Diego, California.
Pearl Pu and Ye Huang. Crossroads Diagnosis. In Proceedings of the European Conference of Artificial Intelligence, pages 704-708, August 1992, Vienna, Austria.
Pearl Pu. An Assembly Sequence Generation Algorithm using Case-based Search Techniques. In Proceedings of the 1992 IEEE International Conference on Robotics and Automation, pages 2425-2430, May 1992, Nice, France.
Boi Faltings and Pearl Pu. Applying Means-Ends Analysis to Spatial Planning. In Proceedings of the Intelligent Robotics and Systems'91, Osaka, Japan, pages 80-85, November 3-5, 1991.
Pearl Pu and Markus Reschberger. Assembly Sequence Planning Using Case-based Reasoning Techniques. In Proceedings of the First International Conference on Artificial Intelligence in Design, Edinburgh, United Kingdom, June 24-27, 1991. (Best Paper Award.)
Pearl Pu and Markus Reschberger. Case-based Assembly Planning. In Proceedings of the DARPA Workshop on Case-based Reasoning, Washington, D.C., pages 245-254, May 8-10, 1991. (This venue was considered a peer-reviewed conference.)
Alberto Izaguirre, Pearl Pu, and John Summers. A New Development in Camera Calibration: Calibrating a pair of Mobile Cameras. In Proceedings of the IEEE International Conference on Robotics and Automation, 2: 34-38, March 1985.
Back to top

Other Peer-Reviewed Full-length Conference and Symposia Papers

Nicolas Jones and Pearl Pu, User Technology Adoption Issues in Recommender Systems. In Proceedings of Networking and Electronic Commerce Research Conference, October 2007 (to appear).
Paolo Viappiani, Pearl Pu and Boi Faltings. Conversational Recommenders with Adaptive Suggestions. In Proceedings of ACM Recommender Systems, Minneapolis, Minnesota, USA, October 19-20, 2007 (to appear).
Jiyong Zhang and Pearl Pu. A Recursive Prediction Algorithm for Collaborative Filtering Recommender Systems. In Proceedings of ACM Recommender Systems, Minneapolis, Minnesota, USA, October 19-20, 2007(to appear).Paolo
Viappiani, Boi Faltings, and Pearl Pu. Stimulating Preferences Expression using Suggestions. In Proceedings of the AAAI Fall Symposia, pages 128-133, November 3-6, Arlington, Virginia, 2005.
Jiyong Zhang and Pearl Pu. Effort and Accuracy Analysis of Choice Strategies for Electronic Product Catalogs. In proceedings of the 20th ACM Symposium on Applied Computing (SAC-2005), track on E-Commerce Technologies, SantaFe, New Mexico, pages 808-814, March 13 -17, 2005.
Pearl Pu and Punit Gupta, Visualizing Reputation and Recommendation in Scientific Literature, In Proceedings of the 10th International Conference on Human - Computer Interaction (HCII '03), Crete, Greece, Lawrence Erlbaum Associates, pages 1126-1130, June 2003.
Pearl Pu and Paul Janecek. Visual Interfaces for Opportunistic Information Seeking. In Proceedings of the 10th International Conference on Human - Computer Interaction ( HCII '03 ), Crete, Greece, Lawrence Erlbaum Associates, pages 1131-1135, June 2003.
Paolo Viappiani, Pearl Pu and Boi Faltings. Acquiring User Preferences for Personal Agents. In Proceedings of the AAAI Fall Symposium, North Falmouth, MA, FS-02-04, pages 53-59, AAAI Press, Menlo Park, California, 2002.
Zoren Pecenovic, Ming Do, Martin Vetterli and Pearl Pu. Integrated Browsing and Searching of Large Image Collections. In Proceedings of the Forth International Conference on Visual Information Systems, Springer Verlag series, pages 279-289, Lyon, France, November 2000.
Gill Bornet dit Vorgea, Pearl Pu, Raymond Clavel, A. Csabai, F. Sprumont, P. Xirouchakis, and M.-T. Ivora. MicroCE: Computer-Aided Support for DFMA Conceptual Design Phase (CE2000). In Proceedings of the 7th ISPE international conference on concurrent engineering, Lyon, France, July 2000
Pearl Pu and Zoren Pecenovic. Dynamic Overview Techniques for Image Retrieval. In Proceedings of the Joint Eurographics - IEEE TCVG Symposium on Visualization, Amsterdam, May 2000.
Christian Frei, Boi Faltings, George Melissargos, and Pearl Pu. IconoNET: a tool for automated bandwidth allocation planning. In Proceedings of the NOMS 2000, IEEE/IFIP Network Operations and Management Symposium, pages 321-334, Hawaii, April 2000.
George Melissargos and Pearl Pu. Interactive Visualization for Resource Allocation Systems. In Proceedings of the Visual Data Exploration and Analysis IV Conference at the IS&T-SPIE Symposium on Electronic Imaging '97, San Jose, California, February 13, 1997.
Pearl Pu and Lisa Purvis. Formalizing Case Adaptation in a Case-based Design System. In Proceedings of the Third International Conference on Artificial Intelligence in Design (AID94), pages 77-91, August 15-18, 1994, Lausanne, Switzerland.
Boi Faltings and Pearl Pu. Applying Means-Ends Analysis to Spatial Planning. In Proceedings of the Spring Symposium of the American Association of Artificial Intelligence, pages 213-218, March 1992, Stanford, California.
Pearl Pu. Extending the Device-Oriented Qualitative Simulation Method to Mechanical Devices. In Proceedings of the Fifth IEEE Conference on Artificial Intelligence Applications, Miami, Florida, pages 29-36, March 1989.
Back to top

Other Publications (Short papers and Workshop papers)

Li Chen and Pearl Pu. The Evaluation of a Hybrid Critiquing System with Preference-based Recommendations Organization. In Proceedings of ACM Recommender Systems, Minneapolis, Minnesota, USA, October 19-20, 2007 (to appear). Short paper.
Jiyong Zhang and Pearl Pu. Refining Preference-Based Search Results Through Bayesian Filtering. In Proceedings of the International Conference on Intelligent User Interfaces (IUI2007), pages 294-297, Hawaii, USA, January 28-31, 2007. Short paper.
James Reilly, Jiyong Zhang, Lorraine McGinty, Pearl Pu and Barry Smyth. A Comparison of Two Compound Critiquing Systems. In Proceedings of the International Conference on Intelligent User Interfaces(IUI2007) , pages 317-320, Hawaii, USA, January 28-31, 2007. Short paper.
Li Chen and Pearl Pu. Trust Building in Recommender Agents. In Proceedings of the Workshop on Web Personalization, Recommender Systems and Intelligent User Interfaces at the 2nd International Conference on E-Business and Telecommunication Networks (ICETE'05), pp.135-145, Reading, UK, October 3-7, 2005.
Paolo Viappiani, Boi Faltings, Vincent Schikel Zuber and Pearl Pu. Stimulating Preference Expression Using Suggestions. In workshop notes of the IJCAI-05 Multidisciplinary Workshop on Advances in Preference Handling, Edinburgh, Scotland, pages 186-191, Aug, 2005.
Patrick Hertzog, Marc Torrens, Pearl Pu and Boi Faltings. Context-aware Computing for Business Traveler Care. In Proceedings of the IADIS International Conference on Applied Computing, Lisbon, Portugal. March 23-26, 2004.
Marc Torrens, Patrick Hertzog, Pearl Pu and Boi Faltings. Towards an Intelligent Mobile Travel Assistant. In Proceedings of the Nineteenth ACM Symposium on Applied Computing (SAC-2004), Nicosia, Cyprus, pages 1208-1209, March 14-17, 2004 (acceptance rate 36%).
Paul Janecek and Pearl Pu. Searching with Semantics: An Interactive Visualization Technique for Exploring an Annotated Image Collection. In Proceedings of the Workshop on Human Computer Interfaces for Semantic Web and Web Applications (HCI-SWWA '03), Springer-Verlag, pages 185-196, November 2003.
Pearl Pu, Pratyush Kumar and Boi Faltings. User-Involved Tradeoff Analysis in Configuration Tasks. In workshop notes, Third International Workshop on User-Interaction in Constraint Satisfaction, Ninth International Conference on Principles and Practice of Constraint Programming, pages 85-102, 2003.
Pearl Pu, Boi Faltings, and Marc Torrens. User-Involved Preferences Elicitation. In workshop notes, Workshop on Configuration, the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI'03), August 2003.
Punit Gupta and Pearl Pu. Social Cues and Awareness for Recommendation Systems. In Proceedings of the International Conference on Intelligent User Interfaces, ACM Press, pages 245-247, January 2003. Short paper.
Pearl Pu and Boi Faltings. Effective Interaction Principles for User-Involved Constraint Problem Solving. In workshop notes of the Second International Workshop on User-Interaction in Constraint Satisfaction, the Eighth International Conference on Principles and Practice of Constraint Programming, pages 77-91, September 2002.
Pu, P. and Faltings, B. Personalized Navigation of Heterogeneous Product Spaces using SmartClient. In Proceedings of the International Conference on Intelligent User Interfaces, ACM Press, pages 212-213, 2002. Short paper.
George Melissargos and Peal Pu. Conceptualizing Bandwidth Allocation in Network Management. In Proceedings of the 1999 workshop on New Paradigms in Information Visualization and Manipulation (NPIVM'99), ACM Conference on Information and Knowledge Management (CIKM'99), page 62-69, Kansas City, USA, November 1999.
G. Melissargos, D. Lalanne and P. Pu. Visualization as Interfacing Tools. In workshop notes of the Swiss Workshop on Collaborative and Distributed Systems, May 2, 1997.
G. Melissargos and P. Pu. Employing interactivity and visualization to augment the process of machine-based rescheduling. In Proceedings of the First International Workshop on Approximate Reasoning in Scheduling (ARS'97) of the International ICSC Symposium on Fuzzy Logic and Applications (ISFL'97), Zurich, February 11, 1997.
P. Pu and B. Faltings. Multimedia Systems for Design. In workshop notes of the Workshop on Intelligent Multimedia Information Retrieval, the International Joint Conference on Artificial Intelligence, Montreal, August 1995.
Pearl Pu. Sigmund: Would you please stop worrying about the cost? On the interactions between creative designers and intelligent machines. In workshop notes of the second workshop on case-based design systems, the Third International Conference on Artificial Intelligence in Design (AID94), pages 39-48, August 1994, Lausanne, Switzerland.
Pearl Pu and James D. Hughes. Solving Scheduling Problems in a Flexible Manufacturing Environment. In workshop notes of the SIGMAN Workshop on Intelligent Manufacturing Technology, Eleventh National Conference on Artificial Intelligence (AAAI 93).
Pearl Pu and Chris Pepin. A Design Methodology for Case-based Design Systems. In Proceedings of the IFIP WG5.2 Workshop on Formal Design Methods for CAD, June 16-19, 1993, Tallinn, Estonia.
Pearl Pu and Ye Huang. Crossroads Diagnosis. In Proceedings of the Third International Workshop on Principles of Diagnosis (DX-92), October 12-15, 1992, Orcas, Island, Washington.
Pearl Pu. Simulating Both Dynamic and Kinematic Behaviors of Mechanisms. In Proceedings of the Third Workshop on Qualitative Reasoning, Stanford, CA, August 1989.
Peter Denno and Pearl Pu. A Model for Conceptual Mechanical Design. A chapter in the Preprints of the third IFIP WG 5.2 workshop on intelligent CAD, edited by H. Yoshikawa and F. Arbab, pages 26-29, 1989.
Pearl Pu and Norman I. Badler. The Implementation of a Design Knowledge Capturing System. In Proceedings of the Second IFIP W.G. 5.2 Workshop on Intelligent CAD, Cambridge, England, pages 410-415, September 1988.
Pearl Pu and N. Badler. Design Knowledge Capture and Causal Simulation. In Proceedings of the First IFIP W.G. 5.2 Workshop on Intelligent CAD, Cambridge, MA, October 1987.

Teaching

Courses

Academic Courses Created and Taught

Introduction to Human Computer Interaction (30-70 students per year), 1998 - present.
USability Analysis through Blended Learning (200- 500 students per year), 2006 – present.
Consumer decision making in online environments: theory and applications (5-15 students, a new Ph.D. level course), 2005 and on demand.
Introduction to Artificial Intelligence (40-50 students per year), 1994 – 1997. Microtechnique department, EPFL
Knowledge Representation in Artificial Intelligence (~10 students, a Ph.D. level course), 1989 – 1993, University of Connecticut.
Constraint Satisfaction Problem Solving (~15 students, a Ph.D. level course) – 1992 -1993, University of Connecticut.

Academic Courses Taught

Discrete Mathematics (30-40 students), 1988 – 1993, University of Connecticut.
Symbolic Programming (30-40 students), 1988 – 1993, University of Connecticut.
Introduction to Programming (> 50 students), 1983 – 1985, University of Pennsylvania
Back to top

Ph.D Students

(2011 expected) Rong Hu, User Involvement Issues in Review and other Social Websites.
(2010 expected) Nicolas Jones, User Issues with Recommender Systems: acceptance, involvement, and trust.
(2008) Li Chen, Preference Elicitation and Trust Building in Decision Agents.
(2008) Jiyong Zhang, Design and Evaluation Issues for User-Centric Online Product Search.
(2007) Paolo Viappiani ( co-advisor ), Preference-based Search with Suggestions.
(2004) Paul Janecek, Semantic Fisheye View for Accessing and Retrieving Multimedia Information.
(2002) Zoran Pecenovic ( co-advisor ), Multimedia Retrieval: indexing, user interaction, and communication issues.
(2000) George Melissargos. Interactive Visualization for Resource Allocation Tasks, Computer Science Department.
(1998) Denis Lalanne. Comind: Computer-aided Creativity for Multi-criteria Search in Design, Microengineering Department, Swiss Federal Institute of Technology in Lausanne, Switzerland.
(1995) Lisa Purvis. Intelligent Design Problem Solving using Case-based and Constraint-based Reasoning, Department of Computer Science and Engineering, Storrs, Connecticut.

Master Students

(2006) David Poirier Quesnel, Master Thesis, Human Machine Interface for Equipment Control Devices,
in collaboration with Secheron, SA.
(2005) Grégory Delajoux, Master Thesis, User Interface Designer /Human Factors, Siemens Corporate Research, USA and EPFL
(2004) Yves Dubugnon, Master Thesis, Evaluation of Exploratory Data Analysis Tools with and without Semantic Fisheye View, EPFL.
(2003) Simon Goumaz, Annotation d’Images dans les Collections Personnelles Digitales, EPFL.
(2002) Punit Kumar Gupta, Master Thesis, Social Navigation of Information Space of Scientific Literature, EPFL and India Institute of Technology Guwahati, India.
(2000) Patrick Hertzog. Interface using Multimodal Agents for a Recommendation System, EPFL.
(2000) Andres Dubi, Master Thesis, Design and Implementation of Electronic Catalogs, EPFL.
(2000) Thierry Jayet, Master Thesis, Catalogues de Solutions pour Conception de Produits Multiples, EPFL.
(1996) Reto Kohlas, Master Thesis, A Cooperative System in Assembly Sequence Problem Solving, University of Fribourg.
(1995) Frank Schnyder. Une Architexture Multi-Agents Pour l’Aide a la Definition d’une Conception, EPFL.
(1993) Christopher G. Pepin. Efficient Design Systems Using Case-Based Techniques, Department of Computer Science and Engineering, Storrs, Connecticut.
(1993) James D. Hughes. An Approach to Scheduling in a Flexible Manufacturing Environment, Department of Computer Science and Engineering, Storrs, Connecticut.
(1993) Ye Huang. Jet Engine Diagnosis, Department of Computer Science and Engineering, Storrs, Connecticut.
(1990) Chengdong Lu. Debugging Qualitative Process Domain Model via Quantity Space, Department of Computer Science and Engineering, Storrs, Connecticut.
(1990) Markus Reschberger. Case-based Reasoning for Assembly Sequence Planning, Department of Computer Science and Engineering, Storrs, Connecticut.

Pearl Pu (), Ph.D.