Publication venue recommendation using profiles based on clustering

TL;DR

This paper tackles the venue recommendation problem by building topic-based subprofiles for venues through global clustering of articles and evaluating them via an IR framework. It introduces two evidence sources—content-based subprofiles and author-based subprofiles—and demonstrates that clustering-based topic subprofiles improve recommendation quality over baselines. A normalized linear fusion, CombLinear, combines content and author signals (with $\lambda$ controlling their balance) to achieve the best performance, highlighting the complementary nature of the information sources. The approach shows practical value for researchers selecting venues and suggests extensions to topic modeling, citation networks, and richer author representations.

Abstract

In this paper we study the venue recommendation problem in order to help researchers to identify a journal or conference to submit a given paper. A common approach to tackle this problem is to build profiles defining the scope of each venue. Then, these profiles are compared against the target paper. In our approach we will study how clustering techniques can be used to construct topic-based profiles and use an Information Retrieval based approach to obtain the final recommendations. Additionally, we will explore how the use of authorship, representing a complementary piece of information, helps to improve the recommendations.

Figures (1)

• Figure 1: acc@10 obtained when using CB+AU features in an IR approach using different profiles and lambda ($\lambda$) values for the linear combination.