News

May, 2020

Our YouTube channel is now available here.

Two of our papers, published in Journal of the Association for Information Science and Technology, receive a high-impact award being in the top 10% most downloaded papers! The papers are: Integrating neurophysiologic relevance feedback in intent modeling for information retrieval and Understanding user behavior in naturalistic information search tasks.


April, 2020

Our paper on interactive GANs accepted for publication at SIGIR 2020. Stay tuned for a preprint.

Our paper on brain responses and information theory, titled "Information gain modulates brain activity evoked by reading" accepted for publication at Scientific Reports (Nature). Paper available here


February, 2020

Our paper on brainsourcing, titled "Brainsourcing: Crowdsourcing Recognition Tasks via Collaborative Brain-Computer Interfacing" accepted for publication at CHI 2020. Paper available here.

Research

The cognitive computing group at the University of Helsinki, led by Academy Research Fellow Tuukka Ruotsalo, conducts research at the intersection of artificial intelligence, cognitive science, and human-computer interaction. We aim at understanding, augmenting, and mimicking human cognitive processes using machine learning; thus developing computing models and interactive applications that can perform intelligently and augment human capabilities. We also focus on utilizing cognitive signals measured from behavior, peripheral physiology, and directly from brains to augment computing models and applications, developing machine learning methods that can learn by observing human behavior and cognition. The methods developed are applied to practical human-computer interaction settings, such as interactive information retrieval, information visualization and generation systems, recommender systems, and brain-computer interfacing applications. Our research is mainly funded by the Academy of Finland and supported by the Helsinki Institute for Information Technology HIIT and the Finnish Center for Artificial Intelligence (FCAI).

Research highlights

Brain-computer Interfacing

We conduct fundamental research into developing new types of implicit brain-computer interfaces and applying them in novel, adaptive and interactive systems. Our current interaction with information retrieval systems rely on explicit interaction. Could we mine the relevance to or interest of the user directly from the human mind? Our research shows, for the first time, that with the help of EEG interpreted via machine learning is indeed possible.

Interactive Information Retrieval

We develop interactive machine learning methods for cognitive modeling of information retrieval, visualization, and information generation, and systems implementing these in real-world information seeking applications. 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.

Cognitive Modeling

We develop machine learning models to model, understand, and decode cognitive states of humans interacting with large information spaces, such as texts, images, and video. We have discovered that human information processing of language stimuli when reading follows information theoretic principles and can be explained by information gain.

Publications

Our research is published in top venues for information retrieval (such as SIGIR, TOIS, JASIST and IPM) and human-computer interaction (such as CHI and IUI), as well as general science outlets (such as CACM and Nature Scientific Reports). Below is a selection of recent publications from our group that represent different research directions, from brain-computer interfacing and cognitive modeling, to interactive information retrieval.

Lauri Kangassalo, Michiel Spapé, Giulio Jacucci, and Tuukka Ruotsalo. 2019. Why do Users Issue Good Queries?: Neural Correlates of Term Specificity. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'19). ACM, New York, NY, USA, 375-384.
Tuukka Ruotsalo, Jaakko Peltonen, Manuel J. A. Eugster, Dorota Głowacka, Patrik Floréen, Petri Myllymäki, Giulio Jacucci, and Samuel Kaski. 2018. Interactive Intent Modeling for Exploratory Search. ACM Trans. Inf. Syst. 36, 4, Article 44 (October 2018), 46 pages.
Tung Vuong, Miamaria Saastamoinen, Giulio Jacucci, and Tuukka Ruotsalo. 2019, Understanding user behavior in naturalistic information search tasks. Journal of the Association for Information Science and Technology, 70: 1248-1261.
Giulio Jacucci, Oswald Barral, Pedram Daee, Michale Wenzel, Baris Serim, Tuukka Ruotsalo, Patrik Pluchino, Jonathan Freeman, Luciano Gamberini, Samuel Kaski, and Benjamin Blankertz. 2019. Integrating neurophysiologic relevance feedback in intent modeling for information retrieval. Journal of the Association for Information Science and Technology, 70: 917-930.
Tuukka Ruotsalo, Giulio Jacucci, Petri Myllymäki, and Samuel Kaski. 2015. Interactive Intent Modeling: Information Discovery Beyond Search. Communications of the ACM, Vol. 58 No. 1, Pages 86-92.
Markus Koskela, Petri Luukkonen, Tuukka Ruotsalo, Mats Sjöberg, and Patrik Floréen. 2018. Proactive Information Retrieval by Capturing Search Intent from Primary Task Context. ACM Trans. Interact. Intell. Syst. 8, 3, Article 20 (July 2018), 25 pages.
Manuel J.A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Ilkka Kosunen, Oswald Barral, Niklas Ravaja, Giulio Jacucci, and Samuel Kaski. 2014. 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.
Tung Vuong, Giulio Jacucci, and Tuukka Ruotsalo. 2017. Watching inside the Screen: Digital Activity Monitoring for Task Recognition and Proactive Information Retrieval. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 1, 3, Article 109 (September 2017), 23 pages.
Valeria Orso, Tuukka Ruotsalo, Jukka Leino, Luciano Gamberini, Giulio Jacucci. 2017. Overlaying social information: The effects on users’ search and information-selection behavior. Information Processing & Management, Volume 53, Issue 6, Pages 1269-1286
Manuel J. A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Oswald Barral, Niklas Ravaja, Giulio Jacucci, and Samuel Kaski. 2016. Natural brain-information interfaces: Recommending information by relevance inferred from human brain signals. Nature Scientific Reports volume 6, Article number: 38580.

A good approximation of our publications is also provided by Google Scholar

People

Group members

Tuukka Ruotsalo
Group leader

Michiel Spapé
Senior researcher
(now officially with Niklas Ravaja's group)

Tung Vuong
Post Graduate Researcher
(supervised with G. Jacucci)

Lauri Kangassalo
Post Graduate Researcher

Keith Davis
Post Graduate Researcher

Carlos de la Torre Ortiz
Post Graduate Researcher

Aleksi Pesonen
Research Assistant
(supervised with G. Jacucci)

Zania Sovijärvi-Spapé
Research Assistant
(Interaction laboratory)

Alumni

  • Oswald Barral(co-supervised with G. Jacucci, at The University of British Columbia)
  • Khalil Klouche (co-supervised with G. Jacucci)
  • Payel Bandyopadhyay (co-supervised with G. Jacucci, at Texas A&M University)
  • Ksenia Konyushkova (at EPFL and DeepMind)
  • Miamaria Saastamoinen (at National Library of Finland)
  • Antti Lipsanen (at Etsimo Healthcare)
  • Sean Weber (at Etsimo Healthcare)
  • Jukka Leino
  • Kseniia Belorustceva

    • Work with us

    If you are interested in joining the group or University of Helsinki Computer or Data Science program in general, we encourage you to apply. You can find more information about our general admission process (for computer science here and for data science here). If you are a foreign student, make sure to read the section for international applicants. If you are already enrolled at the University of Helsinki, either in our data science or computer science program and want to do a master's thesis or apply for a PhD program, you can contact Tuukka directly. We are also constantly hiring research assistants who want to gain research experience during their studies. However, please note that the degree program admissions are handled by the faculty and we cannot enroll students directly.