In this paper, we examine the evolution of the impact of older scholarly articles. We attempt to answer four questions. First, how often are older articles cited and how has this changed over time. Second, how does the impact of older articles vary across different research fields. Third, is the change in the impact of older articles accelerating or slowing down. Fourth, are these trends different for much older articles. To answer these questions, we studied citations from articles published in 1990-2013. We computed the fraction of citations to older articles from articles published each year as the measure of impact. We considered articles that were published at least 10 years before the citing article as older articles. We computed these numbers for 261 subject categories and 9 broad areas of research. Finally, we repeated the computation for two other definitions of older articles, 15 years and older and 20 years and older. There are three conclusions from our study. First, the impact of older articles has grown substantially over 1990-2013. In 2013, 36% of citations were to articles that are at least 10 years old; this fraction has grown 28% since 1990. The fraction of older
With 60M articles in more than 300 language versions, Wikipedia is the largest platform for open and freely accessible knowledge. While the available content has been growing continuously at a rate of around 200K new articles each month, very little attention has been paid to the accessibility of the content. One crucial aspect of accessibility is the integration of hyperlinks into the network so the articles are visible to readers navigating Wikipedia. In order to understand this phenomenon, we conduct the first systematic study of orphan articles, which are articles without any incoming links from other Wikipedia articles, across 319 different language versions of Wikipedia. We find that a surprisingly large extent of content, roughly 15\% (8.8M) of all articles, is de facto invisible to readers navigating Wikipedia, and thus, rightfully term orphan articles as the dark matter of Wikipedia. We also provide causal evidence through a quasi-experiment that adding new incoming links to orphans (de-orphanization) leads to a statistically significant increase of their visibility in terms of the number of pageviews. We further highlight the challenges faced by editors for de-orphanizing
Doctoral theses are an important source of publication in universities, although little research has been carried out on the publications resulting from theses, on so-called derivative articles. This study investigates how derivative articles can be identified through a text analysis based on the full-text of a set of medical theses and the full-text of articles, with which they shared authorship. The text similarity analysis methodology applied consisted in exploiting the full-text articles according to organization of scientific discourse (IMRaD) using the TurnItIn plagiarism tool. The study found that the text similarity rate in the Discussion section can be used to discriminate derivative articles from non-derivative articles. Additional findings were: the first position of the thesis's author dominated in 85% of derivative articles, the participation of supervisors as coauthors occurred in 100% of derivative articles, the authorship credit retained by the thesis's author was 42% in derivative articles, the number of coauthors by article was 5 in derivative articles versus 6.4 coauthors, as average, in non-derivative articles and the time differential regarding the year of thes
We performed a citation analysis on the Web of Science publications consisting of more than 63 million articles and 1.45 billion citations on 254 subjects from 1981 to 2020. We proposed the Article's Scientific Prestige (ASP) metric and compared this metric to number of citations (#Cit) and journal grade in measuring the scientific impact of individual articles in the large-scale hierarchical and multi-disciplined citation network. In contrast to #Cit, ASP, that is computed based on the eigenvector centrality, considers both direct and indirect citations, and provides steady-state evaluation cross different disciplines. We found that ASP and #Cit are not aligned for most articles, with a growing mismatch amongst the less cited articles. While both metrics are reliable for evaluating the prestige of articles such as Nobel Prize winning articles, ASP tends to provide more persuasive rankings than #Cit when the articles are not highly cited. The journal grade, that is eventually determined by a few highly cited articles, is unable to properly reflect the scientific impact of individual articles. The number of references and coauthors are less relevant to scientific impact, but subject
This is an English translation of three articles, originally written in German, by Wilhelm Magnus (1907--1990). The articles are from 1930, 1931, and 1932, respectively, and were the first articles published on one-relator group theory. The first article gives a proof of the famous Freiheitssatz, and many applications of the same. The second investigates various topics in combinatorial group theory, including determining the automorphism group of the figure-eight knot group, listing the subgroups of the modular group, and a proof of the decidability of the word problem in a restricted class of one-relator groups. The third gives a proof of the decidability of the word problem in all one-relator groups. A short preface is provided, summarizing the articles.
Microsoft Academic is a free academic search engine and citation index that is similar to Google Scholar but can be automatically queried. Its data is potentially useful for bibliometric analysis if it is possible to search effectively for individual journal articles. This article compares different methods to find journal articles in its index by searching for a combination of title, authors, publication year and journal name and uses the results for the widest published correlation analysis of Microsoft Academic citation counts for journal articles so far. Based on 126,312 articles from 323 Scopus subfields in 2012, the optimal strategy to find articles with DOIs is to search for them by title and filter out those with incorrect DOIs. This finds 90% of journal articles. For articles without DOIs, the optimal strategy is to search for them by title and then filter out matches with dissimilar metadata. This finds 89% of journal articles, with an additional 1% incorrect matches. The remaining articles seem to be mainly not indexed by Microsoft Academic or indexed with a different language version of their title. From the matches, Scopus citation counts and Microsoft Academic counts
We demonstrate the SciLens News Platform, a novel system for evaluating the quality of news articles. The SciLens News Platform automatically collects contextual information about news articles in real-time and provides quality indicators about their validity and trustworthiness. These quality indicators derive from i) social media discussions regarding news articles, showcasing the reach and stance towards these articles, and ii) their content and their referenced sources, showcasing the journalistic foundations of these articles. Furthermore, the platform enables domain-experts to review articles and rate the quality of news sources. This augmented view of news articles, which combines automatically extracted indicators and domain-expert reviews, has provably helped the platform users to have a better consensus about the quality of the underlying articles. The platform is built in a distributed and robust fashion and runs operationally handling daily thousands of news articles. We evaluate the SciLens News Platform on the emerging topic of COVID-19 where we highlight the discrepancies between low and high-quality news outlets based on three axes, namely their newsroom activity, e
Previous research has shown that journal article quality ratings from the cloud based Large Language Model (LLM) families ChatGPT and Gemini and the medium sized open weights LLM Gemma3 27b correlate moderately with expert research quality scores. This article assesses whether other medium sized LLMs, smaller LLMs, and reasoning models have similar abilities. This is tested with Gemma3 variants, Llama4 Scout, Qwen3, Magistral Small and DeepSeek R1 on a dataset of 2,780 medical, health and life science papers in 6 fields, with two different gold standards, one novel. Few-shot and score averaging approaches are also evaluated. The results suggest that medium-sized LLMs have similar performance to ChatGPT 4o-mini and Gemini 2.0 Flash, but that 1b parameters may often, and 4b sometimes, be too few. Reasoning models did not have a clear advantage. Moreover, averaging scores from multiple identical queries seems to be a universally successful strategy, and there is weak evidence that few-shot prompts (four examples) tend to help. Overall, the results show, for the first time, that smaller LLMs >4b have a substantial capability to rate journal articles for research quality, especially
The aim of this workshop was to enable critical discussion on AI futures using fictional news articles and discussion groups. By collaboratively imagining and presenting future scenarios in a journalistic news article format, participants explored the socio-political, ethical and sustainability factors of AI through an accessible narrative form. Participants engaged in further anticipatory work by analyzing the issues raised by the articles in a group discussion, emphasizing the underlying motivations, assumptions and expectations conveyed within the news articles.
Hoaxes are a recognised form of disinformation created deliberately, with potential serious implications in the credibility of reference knowledge resources such as Wikipedia. What makes detecting Wikipedia hoaxes hard is that they often are written according to the official style guidelines. In this work, we first provide a systematic analysis of similarities and discrepancies between legitimate and hoax Wikipedia articles, and introduce Hoaxpedia, a collection of 311 hoax articles (from existing literature and official Wikipedia lists), together with semantically similar legitimate articles, which together form a binary text classification dataset aimed at fostering research in automated hoax detection. In this paper, We report results after analyzing several language models, hoax-to-legit ratios, and the amount of text classifiers are exposed to (full article vs the article's definition alone). Our results suggest that detecting deceitful content in Wikipedia based on content alone is hard but feasible, and complement our analysis with a study on the differences in distributions in edit histories, and find that looking at this feature yields better classification results than co
In this paper, we attempted to obtain knowledge about how research is conducted, especially how journal articles are produced, by comparing preprints with journal articles that are finally published. First, due to the recent trend of open journals, we were able to secure a certain amount of full-text XML of preprints and journal articles, and verified the technical feasibility of comparing preprints and journal articles. On the other hand, within the scope of this trial, in which we tried to clarify the difference between them based on external criteria such as the number of references and the number of words, and simple document similarity, we could not find a clear difference between preprints and journal articles, or between preprints that became journal articles and those that did not. Even with the machine learning method, the classification accuracy was not high at about 47%. The result that there is no significant difference between preprints and journal articles is a finding that has been shown in previous studies and has been replicated in larger and relatively recent situations. In addition to these, the new findings of this paper are that the differences in many external
This is an English translation of six articles, originally written in Ukrainian, by the semigroup theorist Anton Kazimirovich Sushkevich (1889-1961). The articles date between 1935 and 1939, and were all written in Kharkiv. A preface is also included, giving a summary of the articles and the purpose of the translation.
News articles are driven by the informational sources journalists use in reporting. Modeling when, how and why sources get used together in stories can help us better understand the information we consume and even help journalists with the task of producing it. In this work, we take steps toward this goal by constructing the largest and widest-ranging annotated dataset, to date, of informational sources used in news writing. We show that our dataset can be used to train high-performing models for information detection and source attribution. We further introduce a novel task, source prediction, to study the compositionality of sources in news articles. We show good performance on this task, which we argue is an important proof for narrative science exploring the internal structure of news articles and aiding in planning-based language generation, and an important step towards a source-recommendation system to aid journalists.
Automatic classification of scientific articles based on common characteristics is an interesting problem with many applications in digital library and information retrieval systems. Properly organized articles can be useful for automatic generation of taxonomies in scientific writings, textual summarization, efficient information retrieval etc. Generating article bundles from a large number of input articles, based on the associated features of the articles is tedious and computationally expensive task. In this report we propose an automatic two-step approach for topic extraction and bundling of related articles from a set of scientific articles in real-time. For topic extraction, we make use of Latent Dirichlet Allocation (LDA) topic modeling techniques and for bundling, we make use of hierarchical agglomerative clustering techniques. We run experiments to validate our bundling semantics and compare it with existing models in use. We make use of an online crowdsourcing marketplace provided by Amazon called Amazon Mechanical Turk to carry out experiments. We explain our experimental setup and empirical results in detail and show that our method is advantageous over existing ones.
The citations to a set of academic articles are typically unevenly shared, with many articles attracting few citations and few attracting many. It is important to know more precisely how citations are distributed in order to help statistical analyses of citations, especially for sets of articles from a single discipline and a small range of years, as normally used for research evaluation. This article fits discrete versions of the power law, the lognormal distribution and the hooked power law to 20 different Scopus categories, using citations to articles published in 2004 and ignoring uncited articles. The results show that, despite its popularity, the power law is not a suitable model for collections of articles from a single subject and year, even for the purpose of estimating the slope of the tail of the citation data. Both the hooked power law and the lognormal distributions fit best for some subjects but neither is a universal optimal choice and parameter estimates for both seem to be unreliable. Hence only the hooked power law and discrete lognormal distributions should be considered for subject-and-year-based citation analysis in future and parameter estimates should always
Empirical evidence demonstrates that citations received by scholarly publications follow a pattern of preferential attachment, resulting in a power-law distribution. Such asymmetry has sparked significant debate regarding the use of citations for research evaluation. However, a consensus has yet to be established concerning the historical trends in citation concentration. Are citations becoming more concentrated in a small number of articles? Or have recent geopolitical and technical changes in science led to more decentralized distributions? This ongoing debate stems from a lack of technical clarity in measuring inequality. Given the variations in citation practices across disciplines and over time, it is crucial to account for multiple factors that can influence the findings. This article explores how reference-based and citation-based approaches, uncited articles, citation inflation, the expansion of bibliometric databases, disciplinary differences, and self-citations affect the evolution of citation concentration. Our results indicate a decreasing trend in citation concentration, primarily driven by a decline in uncited articles, which, in turn, can be attributed to the growing
Review articles are a means to structure state-of-the-art literature and to organize the growing number of scholarly publications. However, review articles are suffering from numerous limitations, weakening the impact the articles could potentially have. A key limitation is the inability of machines to access and process knowledge presented within review articles. In this work, we present SmartReviews, a review authoring and publishing tool, specifically addressing the limitations of review articles. The tool enables community-based authoring of living articles, leveraging a scholarly knowledge graph to provide machine-actionable knowledge. We evaluate the approach and tool by means of a SmartReview use case. The results indicate that the evaluated article is successfully addressing the weaknesses of the current review practices.
In recent years, the field of machine learning has seen rapid growth, with applications in a variety of domains, including image recognition, natural language processing, and predictive modeling. In this paper, we explore the application of machine learning to the generation of scientific articles. We present a method for using machine learning to generate scientific articles based on a data set of scientific papers. The method uses a machine-learning algorithm to learn the structure of a scientific article and a set of training data consisting of scientific papers. The machine-learning algorithm is used to generate a scientific article based on the data set of scientific papers. We evaluate the performance of the method by comparing the generated article to a set of manually written articles. The results show that the machine-generated article is of similar quality to the manually written articles.
In this paper, we introduce a dataset of multilingual news articles covering the 2021 Tokyo Olympics. A total of 10,940 news articles were gathered from 1,918 different publishers, covering 1,350 sub-events of the 2021 Olympics, and published between July 1, 2021, and August 14, 2021. These articles are written in nine languages from different language families and in different scripts. To create the dataset, the raw news articles were first retrieved via a service that collects and analyzes news articles. Then, the articles were grouped using an online clustering algorithm, with each group containing articles reporting on the same sub-event. Finally, the groups were manually annotated and evaluated. The development of this dataset aims to provide a resource for evaluating the performance of multilingual news clustering algorithms, for which limited datasets are available. It can also be used to analyze the dynamics and events of the 2021 Tokyo Olympics from different perspectives. The dataset is available in CSV format and can be accessed from the CLARIN.SI repository.
Identifying when and where a news image was taken is crucial for journalists and forensic experts to produce credible stories and debunk misinformation. While many existing methods rely on reverse image search (RIS) engines, these tools often fail to return results, thereby limiting their practical applicability. In this work, we address the challenging scenario where RIS evidence is unavailable. We introduce NewsRECON, a method that links images to relevant news articles to infer their date and location from article metadata. NewsRECON leverages a corpus of over 90,000 articles and integrates: (1) a bi-encoder for retrieving event-relevant articles; (2) two cross-encoders for reranking articles by location and event consistency. Experiments on the TARA and 5Pils-OOC show that NewsRECON outperforms prior work and can be combined with a multimodal large language model to achieve new SOTA results in the absence of RIS evidence. We make our code available.