Diego Kozlowski

Diego Kozlowski, Carolina Pradier, Pierre Benz

Topic Modeling has become a prominent tool for the study of scientific fields, as they allow for a large scale interpretation of research trends. Nevertheless, the output of these models is structured as a list of keywords which requires a manual interpretation for the labelling. This paper proposes to assess the reliability of three LLMs, namely flan, GPT-4o, and GPT-4 mini for topic labelling. Drawing on previous research leveraging BERTopic, we generate topics from a dataset of all the scientific articles (n=34,797) authored by all biology professors in Switzerland (n=465) between 2008 and 2020, as recorded in the Web of Science database. We assess the output of the three models both quantitatively and qualitatively and find that, first, both GPT models are capable of accurately and precisely label topics from the models' output keywords. Second, 3-word labels are preferable to grasp the complexity of research topics.

Francisco Valentini, Diego Kozlowski, Vincent Larivière

Cross-lingual information retrieval (CLIR) helps users find documents in languages different from their queries. This is especially important in academic search, where key research is often published in non-English languages. We present CLIRudit, a novel English-French academic retrieval dataset built from Érudit, a Canadian publishing platform. Using multilingual metadata, we pair English author-written keywords as queries with non-English abstracts as target documents, a method that can be applied to other languages and repositories. We benchmark various first-stage sparse and dense retrievers, with and without machine translation. We find that dense embeddings without translation perform nearly as well as systems using machine translation, that translating documents is generally more effective than translating queries, and that sparse retrievers with document translation remain competitive while offering greater efficiency. Along with releasing the first English-French academic retrieval dataset, we provide a reproducible benchmarking method to improve access to non-English scholarly content.

Maxime Holmberg Sainte-Marie, Diego Kozlowski, Lucía Céspedes et al.

This project aims to compare various language classification procedures, procedures combining various Python language detection algorithms and metadata-based corpora extracted from manually-annotated articles sampled from the OpenAlex database. Following an analysis of precision and recall performance for each algorithm, corpus, and language as well as of processing speeds recorded for each algorithm and corpus type, overall procedure performance at the database level was simulated using probabilistic confusion matrices for each algorithm, corpus, and language as well as a probabilistic model of relative article language frequencies for the whole OpenAlex database. Results show that procedure performance strongly depends on the importance given to each of the measures implemented: for contexts where precision is preferred, using the LangID algorithm on the greedy corpus gives the best results; however, for all cases where recall is considered at least slightly more important than precision or as soon as processing times are given any kind of consideration, the procedure combining the FastSpell algorithm and the Titles corpus outperforms all other alternatives. Given the lack of truly multilingual, large-scale bibliographic databases, it is hoped that these results help confirm and foster the unparalleled potential of the OpenAlex database for cross-linguistic, bibliometric-based research and analysis.

Diego Kozlowski, Dakota S. Murray, Alexis Bell et al.

Racial disparity in academia is a widely acknowledged problem. The quantitative understanding of racial based systemic inequalities is an important step towards a more equitable research system. However, because of the lack of robust information on authors' race, few large scale analyses have been performed on this topic. Algorithmic approaches offer one solution, using known information about authors, such as their names, to infer their perceived race. As with any other algorithm, the process of racial inference can generate biases if it is not carefully considered. The goal of this article is to assess the extent to which algorithmic bias is introduced using different approaches for name based racial inference. We use information from the U.S. Census and mortgage applications to infer the race of U.S. affiliated authors in the Web of Science. We estimate the effects of using given and family names, thresholds or continuous distributions, and imputation. Our results demonstrate that the validity of name based inference varies by race/ethnicity and that threshold approaches underestimate Black authors and overestimate White authors. We conclude with recommendations to avoid potential biases. This article lays the foundation for more systematic and less biased investigations into racial disparities in science.

Diego Kozlowski, Gabriela Lozano, Carla M. Felcher et al.

Cultural products are a source to acquire individual values and behaviours. Therefore, the differences in the content of the magazines aimed specifically at women or men are a means to create and reproduce gender stereotypes. In this study, we compare the content of a women-oriented magazine with that of a men-oriented one, both produced by the same editorial group, over a decade (2008-2018). With Topic Modelling techniques we identify the main themes discussed in the magazines and quantify how much the presence of these topics differs between magazines over time. Then, we performed a word-frequency analysis to validate this methodology and extend the analysis to other subjects that did not emerge automatically. Our results show that the frequency of appearance of the topics Family, Business and Women as sex objects, present an initial bias that tends to disappear over time. Conversely, in Fashion and Science topics, the initial differences between both magazines are maintained. Besides, we show that in 2012, the content associated with horoscope increased in the women-oriented magazine, generating a new gap that remained open over time. Also, we show a strong increase in the use of words associated with feminism since 2015 and specifically the word abortion in 2018. Overall, these computational tools allowed us to analyse more than 24,000 articles. Up to our knowledge, this is the first study to compare magazines in such a large dataset, a task that would have been prohibitive using manual content analysis methodologies.

Diego Kozlowski, Jennifer Dusdal, Jun Pang et al.

Over the last century, we observe a steady and exponentially growth of scientific publications globally. The overwhelming amount of available literature makes a holistic analysis of the research within a field and between fields based on manual inspection impossible. Automatic techniques to support the process of literature review are required to find the epistemic and social patterns that are embedded in scientific publications. In computer sciences, new tools have been developed to deal with large volumes of data. In particular, deep learning techniques open the possibility of automated end-to-end models to project observations to a new, low-dimensional space where the most relevant information of each observation is highlighted. Using deep learning to build new representations of scientific publications is a growing but still emerging field of research. The aim of this paper is to discuss the potential and limits of deep learning for gathering insights about scientific research articles. We focus on document-level embeddings based on the semantic and relational aspects of articles, using Natural Language Processing (NLP) and Graph Neural Networks (GNNs). We explore the different outcomes generated by those techniques. Our results show that using NLP we can encode a semantic space of articles, while with GNN we are able to build a relational space where the social practices of a research community are also encoded.