eprintid: 4030
rev_number: 10
eprint_status: archive
userid: 69
dir: disk0/00/00/40/30
datestamp: 2018-03-09 13:25:14
lastmod: 2018-03-09 13:25:14
status_changed: 2018-03-09 13:25:14
type: monograph
metadata_visibility: show
creators_name: Martini, Andrea
creators_name: Lutov, Artem
creators_name: Gemmetto, Valerio
creators_name: Magalich, Andrii
creators_name: Cardillo, Alessio
creators_name: Constantin, Alex
creators_name: Palchykov, Vasyl
creators_name: Khayati, Mourad
creators_name: Cudre-Mauroux, Philippe
creators_name: Boyarsky, Alexey
creators_name: Ruchayskiy, Oleg
creators_name: Garlaschelli, Diego
creators_name: Rios, Paolo De De
creators_name: Aberer, Karl
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: 
creators_id: diego.garlaschelli@imtlucca.it
creators_id: 
creators_id: 
title: ScienceWISE: Topic Modeling over Scientific Literature Networks
ispublished: submitted
subjects: QC
divisions: EIC
full_text_status: public
monograph_type: working_paper
keywords: Networks
abstract: We provide an up-to-date view on the knowledge management system ScienceWISE (SW) and address issues related to the automatic assignment of articles to research topics. So far, SW has been proven to be an effective platform for managing large volumes of technical articles by means of ontological concept-based browsing. However, as the publication of research articles accelerates, the expressivity and the richness of the SW ontology turns into a double-edged sword: a more fine-grained characterization of articles is possible, but at the cost of introducing more spurious relations among them. In this context, the challenge of continuously recommending relevant articles to users lies in tackling a network partitioning problem, where nodes represent articles and co-occurring concepts create edges between them. In this paper, we discuss the three research directions we have taken for solving this issue: i) the identification of generic concepts to reinforce inter-article similarities; ii) the adoption of a bipartite network representation to improve scalability; iii) the design of a clustering algorithm to identify concepts for cross-disciplinary articles and obtain fine-grained topics for all articles.
date: 2017
date_type: published
publication: http://arxiv.org/abs/1612.07636
publisher: arXiv
pages: 7
id_number: arXiv:1612.07636
institution: IMT Institute for Advanced Studies Lucca
official_url: http://arxiv.org/pdf/1612.07636
citation:   Martini, Andrea and Lutov, Artem and Gemmetto, Valerio and Magalich, Andrii and Cardillo, Alessio and Constantin, Alex and Palchykov, Vasyl and Khayati, Mourad and Cudre-Mauroux, Philippe and Boyarsky, Alexey and Ruchayskiy, Oleg and Garlaschelli, Diego and Rios, Paolo De De and Aberer, Karl  ScienceWISE: Topic Modeling over Scientific Literature Networks.  Working Paper   arXiv       (Submitted)   
document_url: http://eprints.imtlucca.it/4030/1/1612.07636.pdf