In this paper, we present an open data set extracted from the transaction log of the social sciences academic search engine sowiport. The data set includes a filtered set of 484,449 retrieval sessions which have been carried out by sowiport users in the period from April 2014 to April 2015. We propose a description of interactions performed by the academic search engine users that can be used in different applications such as result ranking improvement, user modeling, query reformulation analysis, search pattern recognition.
@article{arxiv.1706.00816,
title = {A Complete Year of User Retrieval Sessions in a Social Sciences Academic Search Engine},
author = {Philipp Mayr and Ameni Kacem},
journal= {arXiv preprint arXiv:1706.00816},
year = {2018}
}
Comments
6 pages, 2 figures, accepted short paper at the 21st International Conference on Theory and Practice of Digital Libraries (TPDL 2017)