Hybrid self-optimized clustering model based on citation links and textual features to detect research topics

The emergence of graphene research topics through interactions within and beyond

Scientific research is an essential stage of the innovation process. However, it remains unclear how a scientific idea becomes applied knowledge and, after that, a commercial product. This paper describes a hypothesis of innovation based on the emergence of new research fields from more mature research fields after interactions between the latter. We focus on graphene, a rising field in materials science, as a case study. First, we used a co-clustering method on titles and abstracts of graphene papers to organize them into four meaningful and robust topics (theory and experimental tests, synthesis and functionalization, sensors, supercapacitors and electrocatalysts). We also demonstrated that they emerged in the order listed. We then tested all topics against the literature on nanotubes and batteries, the possible parent fields of theory and experimental tests, as well as supercapacitors and electrocatalysts. We found incubation signatures for all topics in the nanotube papers collection and weaker incubation signatures for supercapacitors and electrocatalysts in the battery papers collection. Surprisingly, we found and confirmed that the 2004 breakthrough in graphene created a stir in both the nanotube and battery fields. Our findings open the door for a better understanding of how and why new research fields coalesce.

Peer Review

https://publons.com/publon/10.1162/qss_a_00193

Article-level classification of scientific publications: A comparison of deep learning, direct citation and bibliographic coupling

Classification schemes for scientific activity and publications underpin a large swath of research evaluation practices at the organizational, governmental, and national levels. Several research classifications are currently in use, and they require continuous work as new classification techniques becomes available and as new research topics emerge. Convolutional neural networks, a subset of “deep learning” approaches, have recently offered novel and highly performant methods for classifying voluminous corpora of text. This article benchmarks a deep learning classification technique on more than 40 million scientific articles and on tens of thousands of scholarly journals. The comparison is performed against bibliographic coupling-, direct citation-, and manual-based classifications—the established and most widely used approaches in the field of bibliometrics, and by extension, in many science and innovation policy activities such as grant competition management. The results reveal that the performance of this first iteration of a deep learning approach is equivalent to the graph-based bibliometric approaches. All methods presented are also on par with manual classification. Somewhat surprisingly, no machine learning approaches were found to clearly outperform the simple label propagation approach that is direct citation. In conclusion, deep learning is promising because it performed just as well as the other approaches but has more flexibility to be further improved. For example, a deep neural network incorporating information from the citation network is likely to hold the key to an even better classification algorithm.

A comparison of large-scale science models based on textual, direct citation and hybrid relatedness

Recent large-scale bibliometric models have largely been based on direct citation, and several recent studies have explored augmenting direct citation with other citation-based or textual characteristics. In this study we compare clustering results from direct citation, extended direct citation, a textual relatedness measure, and several citation-text hybrid measures using a set of nine million documents. Three different accuracy measures are employed, one based on references in authoritative documents, one using textual relatedness, and the last using document pairs linked by grants. We find that a hybrid relatedness measure based equally on direct citation and PubMed-related article scores gives more accurate clusters (in the aggregate) than the other relatedness measures tested. We also show that the differences in cluster contents between the different models are even larger than the differences in accuracy, suggesting that the textual and citation logics are complementary. Finally, we show that for the hybrid measure based on direct citation and related article scores, the larger clusters are more oriented toward textual relatedness, while the smaller clusters are more oriented toward citation-based relatedness.

Mind the gap: Developments in autonomous driving research and the sustainability challenge

Scientific knowledge on autonomous-driving technology is expanding at a faster-than-ever pace. As a result, the likelihood of incurring information overload is particularly notable for researchers, who can struggle to overcome the gap between information processing requirements and information processing capacity. We address this issue by adopting a multi-granulation approach to latent knowledge discovery and synthesis in large-scale research domains. The proposed methodology combines citation-based community detection methods and topic modelling techniques to give a concise but comprehensive overview of how the autonomous vehicle (AV) research field is conceptually structured. Thirteen core thematic areas are extracted and presented by mining the large data-rich environments resulting from 50 years of AV research. The analysis demonstrates that this research field is strongly oriented towards examining the technological developments needed to enable the widespread rollout of AVs, whereas it largely overlooks the wide-ranging sustainability implications of this sociotechnical transition. On account of these findings, we call for a broader engagement of AV researchers with the sustainability concept and we invite them to increase their commitment to conducting systematic investigations into the sustainability of AV deployment. Sustainability research is urgently required to produce an evidence-based understanding of what new sociotechnical arrangements are needed to ensure that the systemic technological change introduced by AV-based transport systems can fulfill societal functions while meeting the urgent need for more sustainable transport solutions.

Enhancing direct citations: A comparison of relatedness measures for community detection in a large set of PubMed publications

The effects of enhancing direct citations, with respect to publication–publication relatedness measurement, by indirect citation relations (bibliographic coupling, cocitation, and extended direct citations) and text relations on clustering solution accuracy are analyzed. For comparison, we include each approach that is involved in the enhancement of direct citations. In total, we investigate the relative performance of seven approaches. To evaluate the approaches we use a methodology proposed by earlier research. However, the evaluation criterion used is based on MeSH, one of the most sophisticated publication-level classification schemes available. We also introduce an approach, based on interpolated accuracy values, by which overall relative clustering solution accuracy can be studied. The results show that the cocitation approach has the worst performance, and that the direct citations approach is outperformed by the other five investigated approaches. The extended direct citations approach has the best performance, followed by an approach in which direct citations are enhanced by the BM25 textual relatedness measure. An approach that combines direct citations with bibliographic coupling and cocitation performs slightly better than the bibliographic coupling approach, which in turn has a better performance than the BM25 approach.

Research Front Detection and Topic Evolution Based on Topological Structure and the PageRank Algorithm

Research front detection and topic evolution has for a long time been an important direction for research in the informetrics field. However, most previous studies either simply use a citation count for scientific document clustering or assume that each scientific document has the same importance in detecting the clustering theme in a cluster. In this study, utilizing the topological structure and the PageRank algorithm, we propose a new research front detection and topic evolution approach based on graph theory. This approach is made up of three stages: (1) Setting a time window with appropriate length according to the accuracy of scientific documents clustering results and the time delay of a scientific document to be cited, dividing scientific documents into several time windows according to their years of publication, calculating similarities between them according to their topological structure, and clustering them in each time window based on the fast greedy algorithm; (2) combining the PageRank algorithm and keywords’ frequency to detect the clustering theme, which assumes that the more important a scientific document in the cluster is, the greater the possibility that it is cited by the other documents in the same cluster; and (3) reconstructing the cluster graph where nodes represent clusters and edges’ strengths represent the similarities between different clusters, then detecting research front and identifying topic evolution based on the reconstructed cluster graph. To evaluate the performance of our proposed approach, the scientific documents related to data mining and covered by Science Citation Index Expanded (SCI-EXPANDED) or Social Science Citation Index (SSCI) in Web of Science are collected as a case study. The experiment’s results show that the proposed approach can obtain reasonable clustering results, and it is effective for research front detection and topic evolution.

The Impact of Specialization in Journal Networks and Scholarship

BACKGROUND

The use of bibliometrics to evaluate authors, institutions, and journals faces significant challenges in comparing biomedical specialties because of marked differences among fields. Our objective was to evaluate the effect of specialty field and physician numbers on bibliometric parameters.

METHODS

For this bibliometric analysis, data from MDLinx.com and SCImago Journal & Country Rank for 2016 were used to rank the journals. The 2015 Physician Specialty Data Report provided the number of specialists in specific fields. We assessed the means for bibliometric parameters across medical and surgical specialties.

RESULTS

A total of 904 journals within 25 medical and surgical specialties were identified. Medical specialty journals had higher average total citations than did surgical specialty journals (8360 ± 16082 vs. 6217 ± 8743; P = 0.01). Medical specialties with the highest impact factor were oncology (7.8 ± 20.7), psychiatry (4.6 ± 4.0), and neurology (4.4 ± 4.1), whereas surgical specialties were led by urology (2.9 ± 3.3), cardiothoracic surgery (2.9 ± 2.7), and general surgery (2.6 ± 1.7). Impact factor and Eigenfactor score (a measure of both journal citations and caliber) were strongly correlated (r = 0.84, P = 0.0001). Comparison of impact factor per total physicians in the specialty suggested that top-ranked specialty journals were in allergy/immunology, pulmonology, and cardiothoracic surgery. Mean Eigenfactor score per total physicians showed that top journals were in cardiothoracic surgery, rheumatology, and pulmonary medicine.

CONCLUSIONS

Journal bibliometrics, which may strongly influence professional advancement and grant funding, show dramatic differences in ranking after accounting for specialty and physician population. Improved analysis and understanding of available bibliometrics, including their limitations, are necessary to appreciate their role in measuring scholarship.