Lost in Publications? How to Find Your Way in 50 Million Scientific Documents by Machine Learning and Interactive Intent Modelling

Before one can analyze relevant data one must first find it from among
the huge amount of available data. The most common example is
information seeking from large masses of documents, whether it is from
the general web or from large collections. Often the search is
exploratory, and it may be hard to formulate a good query, but
traditional information retrieval systems do not sufficiently help users
to improve unsatisfactory results. In this talk I discuss an improved
system for exploratory search, where users are given power to direct
their search by interacting visually with a model of their search intent.

My talk concentrates on a particular domain: information seeking of
scientific documents. Finding relevant documents is a common task for
researchers, who must navigate big data to keep up to date with ongoing
research and place their own work in context. Current scientific
knowledge includes more than 50 million published articles -- among such
a huge mass of data, how can a system help a researcher find relevant
documents in their field?

We introduce SciNet, an interactive search system that anticipates
the user’s search intents by estimating them from the user’s interaction
with the interface. The estimated intents are visualized on an intent
radar, a radial layout that organizes potential intents as directions in
the information space. The system assists users to direct their search
by allowing feedback to be targeted on keywords representing the
potential intents. Users can provide feedback by moving the keywords on
the intent radar. The system then learns and visualizes improved
estimates and corresponding documents. The resulting user models are
explicit open user models curated by the user during the interactive
information seeking. SciNet has been shown to significantly improve
users’ task performance and the quality of retrieved information without
compromising task execution time. We also show how user models learned
in SciNet can be used to help cold-start recommendation in another
system, the CoMeT talk management system, by cross-system user model
transfer across the systems.

Short biography:
Jaakko Peltonen is an Associate Professor of statistics (data analysis)
at the School of Information Sciences, University of Tampere, Finland
where he leads the Statistical Machine Learning and Exploratory Data
Analysis group; he is also currently an academy research fellow at Aalto
University, Finland, where he is a PI of the Probabilistic Machine
Learning research group. He is an associate editor of Neural Processing
Letters and an editorial board member of Heliyon. He has served in
organizing committees of seven international conferences and one
international summer school, has served in program committees of 31
international conferences/workshops and has performed referee duties for
numerous international journals and conferences. He is an expert in
statistical machine learning methods for exploratory data analysis,
nonlinear dimensionality reduction for visualization of data, and
learning from multiple sources.