Influential tweeters in relation to highly cited articles in altmetric big data

Hassan, Saeed‐Ul; Bowman, Timothy D.; Shabbir, Mudassir; Akhtar, Aqsa; Imran, Mubashir; Aljohani, Naif Radi

doi:10.1007/s11192-019-03044-9

Cited by 18 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the machine-learning models resulted in accurate predictions of impact values and a high accuracy for predicting the top-25% and top-10% highimpact articles. Our results confirm observations in previous studies showing accurate predictions of highly cited articles based on altmetric characteristics and influential tweeters (45,46). Moreover, we complement these findings using multiple impact metrics and a broader collection of article characteristics.…”

Section: Predicting Article Impact With Machine Learningsupporting

confidence: 89%

“…Interestingly, we also show that attention was higher if the study's purpose was described using the term aim rather than goal or objective and if the abstract included many P values. Twitter has known to be central to altmetrics (27,45,49,74,92), and also in our study, Twitter was the dominant source of interaction. However, engagement via news outlets and blogs had a larger effect on attention scores, as well as the type of audience that engaged with the article (i.e., scientists, practitioners and the public).…”

Section: Important Article Characteristicssupporting

confidence: 71%

“…Alternative metrics, such as the Altmetric Attention Score, have received growing interest for the assessment of research performance (26,46,57,79,89,92,105), even more with the increasing support of the DORA declaration (111). Though many articles investigated how attention scores relate to (future) citations (23,24,27,45,51,92), few have assessed the (article) characteristics that relate to a high attention (48). Our results reveal that high attention scores were obtained by reviews and human studies.…”

Section: Important Article Characteristicsmentioning

confidence: 67%

See 2 more Smart Citations

Articles with impact: insights into 10 years of research with machine learning

Zwaard

Leeuw

Meerhoff

et al. 2020

Journal of Applied Physiology

View full text Add to dashboard Cite

Worldwide scientific output is growing faster and faster. Academics should not only publish much and fast, but also publish research with impact. The aim of this study is to use machine learning to investigate characteristics of articles that were published in the Journal of Applied Physiology between 2009 and 2018, and characterize high-impact articles. Article impact was assessed for 4,531 publications by three common impact metrics: the Altmetric Attention Scores, downloads and citations. Additionally, a broad collection of (more than 200) characteristics was collected from the article's title, abstract, authors, keywords, publication, and article engagement. We constructed random forest (RF) regression models to predict article impact and articles with the highest impact (top-25% and top-10% for each impact metric), which were compared to a naïve baseline method. RF models outperformed the baseline models when predicting the impact of unseen articles (p<0.001 for each impact metric). Also, RF models predicted top-25% and top-10% high-impact articles with a high accuracy. Moreover, RF models revealed important article characteristics. Higher impact was observed for articles about exercise, training, performance and V̇O2max, reviews, human studies, articles from large collaborations, longer articles with many references and high engagement by scientists, practitioners and public or via news outlets and videos. Lower impact was shown for articles about respiratory physiology or sleep apnea, editorials, animal studies, and titles with a question mark or a reference to places or individuals. In summary, research impact can be predicted and better understood using a combination of article characteristics and machine learning.

show abstract

Section: Predicting Article Impact With Machine Learningsupporting

confidence: 89%

Section: Important Article Characteristicssupporting

confidence: 71%

Section: Important Article Characteristicsmentioning

confidence: 67%

See 1 more Smart Citation

Articles with impact: insights into 10 years of research with machine learning

Zwaard

Leeuw

Meerhoff

et al. 2020

Journal of Applied Physiology

View full text Add to dashboard Cite

show abstract

“…Comparative analysis of the relationship between the citations and online attention in medical literature highlighted weak correlations and diverse predictors which may affect editorial decisions (Chapa, Haq, & Cifu, 2017). The relationship between significant tweeters and highly cited articles discovered that the significant tweeters exhibited high competency in discriminating top cited and non-top cited articles (Hassan et al, 2019). Connectivity between altmetrics and bibliometrics indicators across academic social networking sites revealed weak correlations and also highlighted the fact that bibliometrics measures are more stable than altmetrics (Ortega, 2015).…”

Section: Literature Reviewmentioning

confidence: 99%

Correlation between the Altmetrics Attention Score (AAS) and the Citation Count (CC): A study based on highly cited breast cancer articles

Jayasekara

Abu

2020

Jnl Univ. Librarians Assoc. Sri Lanka

View full text Add to dashboard Cite

Measuring the impact of a research publication is a vital factor in the scholarly world. Citation count is a single dimension of measuring the impact of a scholarly publication. However, the evolution of the Internet has changed the ways of accessing research publications and research communication. As a result of the Internet, altmetric became a popular tool to measure the research impact. The objective of the article is to identify the correlations between Citation Count and Altmetrics Attention Score based on the top 100 highly cited articles available in the Web of Science database. The scholarly publications related to breast cancer published in 2014 were selected as the target population. Web of Science database was used to collect the bibliographic information and citation count of the highly cited articles. The keyword "Breast Cancer" was used in the 'title' field of WoS and the search was limited to open access journal articles. The search results were arranged according to the times cited from highest to lowest and ranked according to the citation count. The articles within the top 100 rankings according to the citation count were selected as the sample of this study. Altmetrics bookmarklet was used to collect the Altmetrics Attention Scores of the selected articles. Data were analyzed using SPSS 20 software and Microsoft Excel. Spearman's rank order correlation coefficient was used to determine the relationship between Citation Count and Altmetrics Attention Score. The study revealed that there is a positive correlation (r s = .552, p < 0.01) between the Citation Count and the Altmetrics Attention Score.

show abstract

“…Researchers from similar research areas tend to be interested in the same articles. Therefore, many techniques have used citation-based networks to improve document recommendation systems [8][9][10]. Agarwal et al [11] addressed the problems of high dimensionality input data and real-time consumption by introducing a scalable subspace clustering algorithm (SCuBA) approach.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep Neural Network-Based Approach to Measure Scholarly Research Dissemination Using Citations Network

2021

Self Cite

View full text Add to dashboard Cite

We investigated the scientific research dissemination by analyzing the publications and citation data, implying that not all citations are significantly important. Therefore, as alluded to existing state-of-the-art models that employ feature-based techniques to measure the scholarly research dissemination between multiple entities, our model implements the convolutional neural network (CNN) with fastText-based pre-trained embedding vectors, utilizes only the citation context as its input to distinguish between important and non-important citations. Moreover, we speculate using focal-loss and class weight methods to address the inherited class imbalance problems in citation classification datasets. Using a dataset of 10 K annotated citation contexts, we achieved an accuracy of 90.7% along with a 90.6% f1-score, in the case of binary classification. Finally, we present a case study to measure the comprehensiveness of our deployed model on a dataset of 3100 K citations taken from the ACL Anthology Reference Corpus. We employed state-of-the-art graph visualization open-source tool Gephi to analyze the various aspects of citation network graphs, for each respective citation behavior.

show abstract

Influential tweeters in relation to highly cited articles in altmetric big data

Cited by 18 publications

References 24 publications

Articles with impact: insights into 10 years of research with machine learning

Articles with impact: insights into 10 years of research with machine learning

Correlation between the Altmetrics Attention Score (AAS) and the Citation Count (CC): A study based on highly cited breast cancer articles

A Novel Deep Neural Network-Based Approach to Measure Scholarly Research Dissemination Using Citations Network

Contact Info

Product

Resources

About