Machine learning for author name disambiguation is usually conducted on the training and test subsets of labeled data created for a specific task. As a result, disambiguation models learned on heterogeneous labeled data are often inapplicable for other purposes that either do not use the same labeled data or do not make use of any labeled data at all. This article explores the idea of transfer learning in a new context, author name disambiguation. We focus on cases where a disambiguation task lacking labeled training data uses models trained on labeled data generated for other tasks. For this purpose, two labeled source datasets are used for training of disambiguation models to be applied to three test target datasets that are deficient of labeled training data. Our results show that transfer learning can produce disambiguation performances similar to those achievable by traditional machine learning in which training and test datasets come from the same labeled data source. The good performance through transfer learning are possible when training source datasets have similar feature distributions as test target datasets. This study suggests that through transfer learning, rich disambiguation models in previous studies can be retained and reused across ambiguous bibliographic data from different fields and data sources, motivating further research on how to correct feature distribution differences between source and target datasets to expand the application of transfer learning in author name disambiguation beyond the model sharing explored in this research.

Mathematics is an important and hotly contested aspect of U.S. postsecondary education. Its importance for academics and careers and the extent and impact of math achievement disparities are all subject of longstanding debate. Yet there is surprisingly little research into how much and what types of mathematics courses are taken by U.S. undergraduates and the extent of math achievement differentials among students. This article advances the understanding of math course taking by developing course-taking metrics for a nationally representative cohort of bachelor’s graduates. Using NCES transcript data to construct consistent measures of mathematics and quantitative course taking, our analysis finds large variability both within and between STEM/non-STEM majors and a large population of non-STEM graduates earning mathematics credits comparable to their peers in STEM fields. Mathematics course taking differs substantially from course taking in other subjects. We also find that often-observed gender differentials are a function of major, not gender, with females in the most mathematics-intensive programs earning as many or more mathematics credits than their male peers.

In author name disambiguation, author forenames are used to decide which name instances are disambiguated together and how much they are likely to refer to the same author. Despite such a crucial role of forenames, their effect on the performance of heuristic (string matching) and algorithmic disambiguation is not well understood. This study assesses the contributions of forenames in author name disambiguation using multiple labeled data sets under varying ratios and lengths of full forenames, reflecting real-world scenarios in which an author is represented by forename variants (synonym) and some authors share the same forenames (homonym). The results show that increasing the ratios of full forenames substantially improves both heuristic and machine-learning-based disambiguation. Performance gains by algorithmic disambiguation are pronounced when many forenames are initialized or homonyms are prevalent. As the ratios of full forenames increase, however, they become marginal compared to those by string matching. Using a small portion of forename strings does not reduce much the performances of both heuristic and algorithmic disambiguation methods compared to using full-length strings. These findings provide practical suggestions, such as restoring initialized forenames into a full-string format via record linkage for improved disambiguation performances. © 2019 ASIS&T

y Conference publications in computer science (CS) have attracted scholarly attention due to their unique status as a main research outlet, unlike other science fields where journals are dominantly used for communicating research findings. One frequent research question has been how different conference and journal publications are, considering an article as a unit of analysis. This study takes an author-based approach to analyze the publishing patterns of 517,763 scholars who have ever published both in CS conferences and journals for the last 57 years, as recorded in DBLP. The analysis shows that the majority of CS scholars tend to make their scholarly debut, publish more articles, and collaborate with more coauthors in conferences than in journals. Importantly, conference articles seem to serve as a distinct channel of scholarly communication, not a mere preceding step to journal publications: coauthors and title words of authors across conferences and journals tend not to overlap much. This study corroborates findings of previous studies on this topic from a distinctive perspective and suggests that conference authorship in CS calls for more special attention from scholars and administrators outside CS who have focused on journal publications to mine authorship data and evaluate scholarly performance.

Clustering results in author name disambiguation are often evaluated by measures such as Cluster-F, K-metric, Pairwise-F, Splitting and Lumping Error, and B-cubed. Although these measures have different evaluation approaches, this paper shows that they can be calculated in a single framework by a set of common steps that compare truth and predicted clusters through two hash tables recording information about name instances with their predicted cluster indices and frequencies of those indices per truth cluster. This integrative calculation reduces greatly calculation runtime, which is scalable to a clustering task involving millions of name instances within a few seconds. During the integration process, B-cubed and K-metric are shown to produce the same precision and recall scores. In addition, name instance pairs for Pairwise-F are counted using a heuristic, which enables the proposed method to surpass a state-of-the-art algorithm in speedy calculation. Details of the integrative calculation are described with examples and pseudo-code to assist scholars to implement each measure easily and validate the correctness of implementation. The integrative calculation will help scholars compare similarities and differences of multiple measures before they select ones that characterize best the clustering performances of their disambiguation methods.

The relationship between education policy and workforce policy has long been uneasy. It is widely believed in many quarters of American society that the U.S. education system is in decline and, what’s more, that it bears significant responsibility for a wide range of social ills, including stagnant wages, increasing inequality, high unemployment, and overall economic lethargy. However, as analyzed in this paper, the preponderance of evidence suggests that the U.S. education system has produced ample supplies of students to respond to STEM labor market demand. The “pipeline” of STEM-potential students is similarly strong and expanding.

Several studies have found that collaboration networks are scale-free, proposing that such networks can be modeled by specific network evolution mechanisms like preferential attachment. This study argues that collaboration networks can look more or less scale-free depending on the methods for resolving author name ambiguity in bibliographic data. Analyzing networks constructed from multiple datasets containing 3.4 M similar to 9.6 M publication records, this study shows that collaboration networks in which author names are disambiguated by the commonly used heuristic, i.e., forename-initial-based name matching, tend to produce degree distributions better fitted to power-law slopes with the typical scaling parameter (2 < alpha < 3) than networks disambiguated by more accurate algorithm-based methods. Such tendency is observed across collaboration networks generated under various conditions such as cumulative years, 5- and 1-year sliding windows, and random sampling, and through simulation, found to arise due mainly to artefactual entities created by inaccurate disambiguation. This cautionary study calls for special attention from scholars analyzing network data in which entities such as people, organization, and gene can be merged or split by improper disambiguation.

In supervised machine learning for author name disambiguation, negative training data are often dominantly larger than positive training data. This paper examines how the ratios of negative to positive training data can affect the performance of machine learning algorithms to disambiguate author names in bibliographic records. On multiple labeled datasets, three classifiers-Logistic Regression, Naive Bayes, and Random Forest-are trained through representative features such as coauthor names, and title words extracted from the same training data but with various positive-to-negative training data ratios. Results show that increasing negative training data can improve disambiguation performance but with a few percent of performance gains and sometimes degrade it. Logistic and Naive Bayes learn optimal disambiguation models even with a base ratio (1:1) of positive and negative training data. Also, the performance improvement by Random Forest tends to quickly saturate roughly after 1:10 similar to 1:15. These findings imply that contrary to the common practice using all training data, name disambiguation algorithms can be trained using part of negative training data without degrading much disambiguation performance while increasing computational efficiency. This study calls for more attention from author name disambiguation scholars to methods for machine learning from imbalanced data.

Author name ambiguity in a digital library may affect the findings of research that mines authorship data of the library. This study evaluates author name disambiguation in DBLP, a widely used but insufficiently evaluated digital library for its disambiguation performance. In doing so, this study takes a triangulation approach that author name disambiguation for a digital library can be better evaluated when its performance is assessed on multiple labeled datasets with comparison to baselines. Tested on three types of labeled data containing 5000 to 6 M disambiguated names, DBLP is shown to assign author names quite accurately to distinct authors, resulting in pairwise precision, recall, and F1 measures around 0.90 or above overall. DBLP's author name disambiguation performs well even on large ambiguous name blocks but deficiently on distinguishing authors with the same names. Compared to other disambiguation algorithms, DBLP's disambiguation performance is quite competitive, possibly due to its hybrid disambiguation approach combining algorithmic disambiguation and manual error correction. A discussion follows on strengths and weaknesses of labeled datasets used in this study for future efforts to evaluate author name disambiguation on a digital library scale.

Intelligent tutoring systems are known for providing customized learning opportunities for thousands of users. One feature of many systems is differentiating the amount of practice users receive. To do this, some systems rely on a threshold of consecutive correct responses. For instance, Khan Academy used to use ten correct in a row and now uses five correct in a row as the mastery threshold. The present research uses a series of randomized control trials, conducted in an online learning platform (eg., ASSISTments.org), to explore the effects of different thresholds of consecutive correct responses on learning. Results indicate that despite spending significantly more time practicing there is no significant difference on learning between two, three, four, or five consecutive correct responses. This suggests that systems, and MOOCS, can employ the simple rule of two or three consecutive correct responses when determining the amount of practice provided to users.