Inferring relevance from eye movements with wrong models

Thumbnail Image
Journal Title
Journal ISSN
Volume Title
Doctoral thesis (article-based)
Checking the digitized thesis and permission for publishing
Instructions for the author
Degree programme
Verkkokirja (1287 KB, 76 s.)
Statistical inference forms the backbone of modern science. It is often viewed as giving an objective validation for hypotheses or models. Perhaps for this reason the theory of statistical inference is often derived with the assumption that the "truth" is within the model family. However, in many real-world applications the applied statistical models are incorrect. A more appropriate probabilistic model may be computationally too complex, or the problem to be modelled may be so new that there is little prior information to be incorporated. However, in statistical theory the theoretical and practical implications of the incorrectness of the model family are to a large extent unexplored. This thesis focusses on conditional statistical inference, that is, modeling of classes of future observations given observed data, under the assumption that the model is incorrect. Conditional inference or prediction is one of the main application areas of statistical models which is still lacking a conclusive theoretical justification of Bayesian inference. The main result of the thesis is an axiomatic derivation where, given an incorrect model and assuming that the utility is conditional likelihood, a discriminative posterior yields a distribution on model parameters which best agrees with the utility. The devised discriminative posterior outperforms the classical Bayesian joint likelihood-based approach in conditional inference. Additionally, a theoretically justified expectation maximization-type algorithm is presented for obtaining conditional maximum likelihood point estimates for conditional inference tasks. The convergence of the algorithm is shown to be more stable than in earlier partly heuristic variants. The practical application field of the thesis is inference of relevance from eye movement signals in an information retrieval setup. It is shown that relevance can be predicted to some extent, and that this information can be exploited in a new kind of task, proactive information retrieval. Besides making it possible to design new kinds of engineering applications, statistical modeling of eye tracking data can also be applied in basic psychological research to make hypotheses of cognitive processes affecting eye movements, which is the second application area of the thesis.
conditional inference, incorrect model, probabilistic inference, eye movements, proactive information retrieval
Other note
  • [Publication 1]: Jarkko Salojärvi, Ilpo Kojo, Jaana Simola, and Samuel Kaski. 2003. Can relevance be inferred from eye movements in information retrieval? In: Proceedings of the 4th Workshop on Self-Organizing Maps (WSOM 2003). Hibikino, Japan. 11-14 September 2003, pages 261-266. © 2003 WSOM'03 Organizing Committee. By permission.
  • [Publication 2]: Jarkko Salojärvi, Kai Puolamäki, and Samuel Kaski. 2004. Relevance feedback from eye movements for proactive information retrieval. In: Janne Heikkilä, Matti Pietikäinen, and Olli Silvén (editors). Proceedings of the Workshop on Processing Sensory Information for Proactive Systems (PSIPS 2004). Oulu, Finland. 14-15 June 2004, pages 37-42. © 2004 by authors.
  • [Publication 3]: Jarkko Salojärvi, Kai Puolamäki, and Samuel Kaski. 2005. Implicit relevance feedback from eye movements. In: Włodzisław Duch, Janusz Kacprzyk, Erkki Oja, and Sławomir Zadrożny (editors). Proceedings of the 15th International Conference on Artificial Neural Networks: Biological Inspirations (ICANN 2005). Warsaw, Poland. 11-15 September 2005. Berlin, Germany. Springer. Lecture Notes in Computer Science, volume 3696, pages 513-518. © 2005 by authors and © 2005 Springer Science+Business Media. By permission.
  • [Publication 4]: Kai Puolamäki, Jarkko Salojärvi, Eerika Savia, Jaana Simola, and Samuel Kaski. 2005. Combining eye movements and collaborative filtering for proactive information retrieval. In: Gary Marchionini, Alistair Moffat, John Tait, Ricardo Baeza-Yates, and Nivio Ziviani (editors). Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2005). Salvador, Brazil. 15-19 August 2005. New York, USA. ACM Press, pages 146-153. © 2005 Association for Computing Machinery (ACM). By permission.
  • [Publication 5]: Jarkko Salojärvi, Kai Puolamäki, and Samuel Kaski. 2005. Expectation maximization algorithms for conditional likelihoods. In: Luc De Raedt and Stefan Wrobel (editors). Proceedings of the 22nd International Conference on Machine Learning (ICML 2005). Bonn, Germany. 7-11 August 2005. New York, USA. ACM Press. ACM International Conference Proceeding Series, volume 119, pages 753-760. © 2005 by authors.
  • [Publication 6]: Jarkko Salojärvi, Kai Puolamäki, and Samuel Kaski. 2005. On discriminative joint density modeling. In: João Gama, Rui Camacho, Pavel Brazdil, Alípio Jorge, and Luís Torgo (editors). Proceedings of the 16th European Conference on Machine Learning (ECML 2005). Porto, Portugal. 3-7 October 2005. Berlin, Germany. Springer. Lecture Notes in Artificial Intelligence, volume 3720, pages 341-352. © 2005 by authors and © 2005 Springer Science+Business Media. By permission.
  • [Publication 7]: Jarkko Salojärvi, Kai Puolamäki, Eerika Savia, and Samuel Kaski. 2008. Inference with discriminative posterior. arXiv:0807.3470v2 [stat.ML]. Submitted to a journal. © 2008 by authors.
  • [Publication 8]: Jaana Simola, Jarkko Salojärvi, and Ilpo Kojo. 2008. Using hidden Markov model to uncover processing states from eye movements in information search tasks. Cognitive Systems Research, volume 9, number 4, pages 237-251. © 2008 by authors and © 2008 Elsevier Science. By permission.