EEG reveals information essential to users
Our researchers have, first in the world, shown that recommending new information from the World Wide Web is possible by detecting relevance directly from human brain signals.
A strategic HIIT-wide research focus
We have developed a technique called interactive intent modeling that allows humans to direct exploratory search. The technique has been implemented in a real-world search engine SciNet. The search engine anticipates user's search intents and visualizes them on a novel "Intent Radar" screen. Check out our papers in CACM and at IUI'15, CIKM'13, and IUI'13 (best paper award).
Our current interaction with information retrieval systems rely on explicit interaction. Could we mine the relevance or interest of the user directly from the human mind? Our research shows, for the first time, that this is indeed possible with the help of EEG interpreted with machine learning. Check out our Sci. Rep. article, and SIGIR'14 and SIGIR'15 workshop papers.
We have created a five-meter-wide MultiTouch wall with Kinect 3D motion sensing camera. The reseachers have solved the problem how to attract people to use the multitouch display wall. The multitouch wall with 3D motion sensing cameras reacts to new potential users passing by and lures them to touch the wall and explore the content when they approach it. Check out our papers at TEI'14 and ITS'13.
Augmented search, research, and knowledge work are the main themes of the HIIT-wide research initiative that is a strategic research focus of HIIT. It is a big multidisciplinary project spanning several research groups of Helsinki Institute for Information Technology HIIT at Aalto University and University of Helsinki. Several research groups ranging from Human-Computer Interaction to Machine Learning and Complex Systems Computation collaborate to produce cutting edge research and demonstrations that go beyond individual research papers. The main themes of the project are augmented search, research, and knowledge work. The project investigates how Human-Computer Interaction and Probabilistic Machine Learning can be combined to a loop that will increase, by order of magnitude, the effectiveness of search and knowledge work. We are applying our research to scientific data and work environments as well as industrial settings. The methods and tools will be able to better utilize the massive explosion of raw data, documents, distributed information and link structures between these, and sensory information recorded from the users. The methods and pilot applications are expected to revolutionize our work practices in data-driven fields such as modern biology, business intelligence, and others. In particular improving the general problem solving method of science, research, and development, in collaboration with the other fields, is the best way for our research community to contribute to solving the grand challenges of humanity.
How to join the Focus Area? Contact Tuukka.Ruotsalo(a)aalto.fi or Giulio.Jacucci(a)helsinki.fi to get started.
HIIT-Wide Focus Area research has been extended to a large national project Revolution of Knowledge Work. It is funded by Tekes, as a large strategic opening. The project creates information-seeking and sense-making methods supporting a revolution of knowledge work by combining the potential of human creativity and the capability of computers to handle data.
MindSee aims to develop an information seeking application that exemplifies the fruitful symbiosis of modern Brain Computer Interface technology with real-world Human Computer Interaction. The result will be a cutting-edge information retrieval system that outperforms state-of-the-art tools by more than doubling the performance of information seeking in realistic tasks.
Manuel J. A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Oswald Barral, Niklas Ravaja, Giulio Jacucci and Samuel Kaski. Natural brain-information interfaces: Recommending information by relevance inferred from human brain signals. Scientific Reports 6, 38580 (2016). DOI=10.1038/srep38580
Petri Luukkonen, Markus Koskela, Patrik Floréen. LSTM-Based Predictions for Proactive Information Retrieval. Neu-IR '16 SIGIR Workshop on Neural Information Retrieval. July 2016. arXiv:1606.06137
Pedram Daee, Joel Pyykkö, Dorota Glowacka, and Samuel Kaski. Interactive Intent Modeling from Multiple Feedback Domains. In Proceedings of the 21st International Conference on Intelligent User Interfaces (IUI '16). ACM, New York, NY, USA, 71-75. March 2016. DOI=10.1145/2856767.2856803
Ilkka Kosunen, Mikko Salminen, Simo Järvelä, Antti Ruonala, Niklas Ravaja, and Giulio Jacucci. RelaWorld: Neuroadaptive and Immersive Virtual Reality Meditation System. In Proceedings of the 21st International Conference on Intelligent User Interfaces (IUI '16). ACM, New York, NY, USA, 208-217. March 2016. DOI=10.1145/2856767.2856796
Kumaripaba Athukorala, Alan Medlar, Antti Oulasvirta, Giulio Jacucci, and Dorota Glowacka. Beyond Relevance: Adapting Exploration/Exploitation in Information Retrieval. In Proceedings of the 21st International Conference on Intelligent User Interfaces (IUI '16). ACM, New York, NY, USA, 359-369. March 2016. DOI=10.1145/2856767.2856786
Antti Kangasrääsiö, Yi Chen, Dorota Glowacka, and Samuel Kaski. Dealing with Concept Drift in Exploratory Search: An Interactive Bayesian Approach. In Companion Publication of the 21st International Conference on Intelligent User Interfaces (IUI '16 Companion). ACM, New York, NY, USA, 62-66. March 2016. DOI=10.1145/2876456.2879487
Kumaripaba Ahukorala, Alan Medlar, Kalle Ilves, and Dorota Głowacka. Balancing Exploration and Exploitation: Empirical Parameterization of Exploratory Search Systems. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management (CIKM '15). ACM, New York, NY, USA, 1703-1706. October 2015. DOI=10.1145/2806416.2806609
Santayan Hore, Dorota Głowacka, Ilkka Kosunen, Kumaripaba Athukorala, and Giulio Jacucci. FutureView: Enhancing Exploratory Image Search. Workshop Interfaces and Human Decision Making for Recommender Systems at the Conference RecSys 2015. Vienna, Austria. September 2015. [pdf]
Manuel J. A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Ilkka Kosunen, Oswald Barral, Niklas Ravaja, Giulio Jacucci, and Samuel Kaski. Predicting Relevance of Text from Neuro-Physiology. SIGIR 2015 Workshop on Neuro-Physiological Methods in IR Research (NeuroIR 2015). August 2015. [pdf]
Salvatore Andolina, Khalil Klouche, Diogo Cabral, Tuukka Ruotsalo, and Giulio Jacucci. InspirationWall: Supporting Idea Generation Through Automatic Information Exploration. In Proceedings of the 2015 ACM SIGCHI Conference on Creativity and Cognition (C&C '15). ACM, New York, NY, USA, 103-106. June 2015. DOI=10.1145/2757226.2757252
Kalle Ilves, Alan Medlar, and Dorota Głowacka. Visualizing User Model in Exploratory Search Tasks. In Proceedings of 4th Workshop on Machine Learning for Interactive Systems (MLIS-2015), Lille, France, July 2015. JMLR: W&CP volume 43. [pdf]
Antti Kangasrääsiö, Dorota Głowacka, and Samuel Kaski. Improving Controllability and Predictability of Interactive Recommendation Interfaces for Exploratory Search. In Proceedings of the 20th International Conference on Intelligent User Interfaces (IUI '15). ACM, New York, NY, USA, 247-251. March-April 2015. DOI=10.1145/2678025.2701371
Salvatore Andolina, Khalil Klouche, Jaakko Peltonen, Mohammad Hoque, Tuukka Ruotsalo, Diogo Cabral, Arto Klami, Dorota Głowacka, Patrik Floréen, and Giulio Jacucci. IntentStreams: Smart Parallel Search Streams for Branching Exploratory Search. In Proceedings of the 20th International Conference on Intelligent User Interfaces (IUI '15). ACM, New York, NY, USA, 300-305. March-April 2015. DOI=10.1145/2678025.2701401
Oswald Barral, Manuel J.A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Ilkka Kosunen, Niklas Ravaja, Samuel Kaski, and Giulio Jacucci. Exploring Peripheral Physiology as a Predictor of Perceived Relevance in Information Retrieval. In Proceedings of the 20th International Conference on Intelligent User Interfaces (IUI '15). ACM, New York, NY, USA, 389-399. March-April 2015. DOI=10.1145/2678025.2701389
Yuan Gao, Kalle Ilves, and Dorota Głowacka. OfficeHours: A System for Student Supervisor Matching through Reinforcement Learning. In Proceedings of the 20th International Conference on Intelligent User Interfaces Companion (IUI Companion '15). ACM, New York, NY, USA, 29-32. March-April 2015. DOI=10.1145/2732158.2732189
Tuukka Ruotsalo, Giulio Jacucci, Petri Myllymäki, and Samuel Kaski. Interactive intent modeling: information discovery beyond search. Commun. ACM 58, 1 (January 2015), 86-92. DOI=10.1145/2656334
Kumaripaba Athukorala, Antti Oulasvirta, Dorota Głowacka, Jilles Vreeken, and Giulio Jacucci. Narrow or Broad?: Estimating Subjective Specificity in Exploratory Search. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management (CIKM '14). ACM, New York, NY, USA, 819-828. November 2014. DOI=10.1145/2661829.2661904
Manuel J.A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Ilkka Kosunen, Oswald Barral, Niklas Ravaja, Giulio Jacucci, and Samuel Kaski. Predicting term-relevance from brain signals. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval (SIGIR '14). ACM, New York, NY, USA, 425-434. July 2014. DOI=10.1145/2600428.2609594
Tuukka Ruotsalo, Jaakko Peltonen, Manuel J.A. Eugster, Dorota Glowacka, Aki Reijonen, Giulio Jacucci, Petri Myllymäki, and Samuel Kaski. Intentradar: search user interface that anticipates user's search intents. In CHI '14 Extended Abstracts on Human Factors in Computing Systems (CHI EA '14). ACM, New York, NY, USA, 455-458. April-May 2014. DOI=10.1145/2559206.2574807
Kai Kuikkaniemi, Vilma Lehtinen, Matti Nelimarkka, Max Vilkki, Jouni Ojala, and Giulio Jacucci. Designing for presenters at public walk-up-and-use displays. In Proceedings of the 8th International Conference on Tangible, Embedded and Embodied Interaction (TEI '14). ACM, New York, NY, USA, 225-232. February 2014. DOI=10.1145/2540930.2540949
Tuukka Ruotsalo, Jaakko Peltonen, Manuel Eugster, Dorota Głowacka, Ksenia Konyushkova, Kumaripaba Athukorala, Ilkka Kosunen, Aki Reijonen, Petri Myllymäki, Giulio Jacucci, and Samuel Kaski. Directing exploratory search with interactive intent modeling. In Proceedings of the 22nd ACM international conference on Conference on information & knowledge management (CIKM '13). ACM, New York, NY, USA, 1759-1764. October-November 2013. DOI=10.1145/2505515.2505644
Kai Kuikkaniemi, Max Vilkki, Jouni Ojala, Matti Nelimarkka, and Giulio Jacucci. Introducing Kupla UI: a generic interactive wall user interface based on physics modeled spherical content widgets. In Proceedings of the 2013 ACM international conference on Interactive tabletops and surfaces (ITS '13). ACM, New York, NY, USA, 301-304. October 2013. DOI=10.1145/2512349.2514588
Dorota Glowacka, Tuukka Ruotsalo, Ksenia Konuyshkova, Kumaripaba Athukorala, Samuel Kaski, and Giulio Jacucci. 2013. Directing exploratory search: reinforcement learning from user interactions with keywords. In Proceedings of the 2013 international conference on Intelligent user interfaces (IUI '13). ACM, New York, NY, USA, 117-128. March 2013. DOI=10.1145/2449396.2449413