Fig 1 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Traditional citation analyses use quantitative methods only, even though there is meaning in the sentences containing citations within the text. This article analyzes three citation meanings: sentiment, role, and function. We compare citation meanings patterns between fields of science and propose an appropriate deep learning model to classify the...
Similar publications
p>Sentence segmentation that breaks textual data strings into individual sentences is an important phase in natural language processing (NLP). Each word in the string that is added a punctuation mark such as a period, question mark, or exclamation point, becomes the location for splitting the string. Humans can easily see the punctuation and split...
Citations
... Sentiment analysis of citations has attracted particular attention for two main reasons: First, to improve bibliometric metrics by focusing primarily on the quality rather than quantity of citations, with the aim of reducing bias and providing evidence-based support for writing. Second, to detect non-reproducible research, i.e., the identification of research papers or results that cannot be replicated or verified by other researchers, especially in the biomedical field, where unfavorable attitudes may be early indicators of the non-reproducibility of research, thus saving time and resources [28]. Therefore, although positive polarity citations have a significant impact on science, as they can enhance the validity and reliability of findings and even promote the reputation and career of researchers, the study by Catalini et al. [29], however, equally highlights that negative citations can also play an important role in science. ...
Sentiment Analysis in text, especially text containing scientific citations, is an emerging research field with important applications in the research community. This review explores the field of sentiment analysis by focusing on the interpretation of citations, presenting a detailed description of techniques and methods ranging from lexicon-based approaches to Machine and Deep Learning models. The importance of understanding both the emotion and the intention behind citations is emphasized, reflecting their critical role in scientific communication. In addition, this study presents the challenges faced by researchers (such as complex scientific terminology, multilingualism, and the abstract nature of scientific discourse), highlighting the need for specialized language processing techniques. Finally, future research directions include improving the quality of datasets as well as exploring architectures and models to improve the accuracy of sentiment detection.
... This limited approach fails to provide a comprehensive understanding since there may be preceding or following sentences that discuss the same citing paper with different intentions. Consequently, a single-sentence context is insufficient for thorough citation analysis [6]. To overcome the limitation posed by a single citation sentence or a fixed window of citation sentences, we advocate to consider multi-sentence-based citation context along with its potential intents [7]. ...
... Additionally, they performed intent classification on the SciCite dataset and achieved an 85% accuracy using XLNet. Budi & Yaniasih, conducted experiments on 9173 citation sentences from five science disciplines: Food, Energy, Health, Social, and Computer [6]. They employed a CNN-based multi-task learning approach for citation sentiment classification (positive, negative, and neutral), citation role classification (supplemental, result, method, and data), and citation function classification (introducing, relating, utilizing, explaining, and comparing). ...
Citation analysis has garnered significant attention in academia, particularly in the realm of scientometrics analysis. Most studies related to citation analysis focus on quantitative aspects, assigning equal weight to every citation regardless of its placement within the paper. However, understanding the distribution of citation weight across different sections of a research article is crucial for citation analysis and impact assessment. Therefore, the analysis of citation intent becomes a pivotal task in determining the qualitative importance of a citation within a scientific article. In this context, we undertook two essential tasks related to citation analysis: citation length analysis and citation intent analysis. Through citation length analysis, we identified the optimal number of citation sentences to consider around a cited sentence. Simultaneously, citation intent analysis aimed to categorize citations into seven distinct types, namely background, motivation, uses, extends, similarities, differences, and future work. For the latter task, we introduced two novel architectures based on graph neural networks, namely CiteIntentRoBERTaGCN and CiteIntentRoBERTaGAT. The performance of these proposed models was evaluated on five multi-intent datasets curated from 1,200 research papers, considering different context lengths. The results demonstrated that the proposed models achieved state-of-the-art performance.
... Concerning alternative metrics, a large stream of research highlighted the need for developing metrics based on better data (Mas-Bleda & Thelwall, 2016;Molas-Gallart & Ràfols, 2018). Many advocates for using better algorithms to address problematic issues of bibliometric databases such as name disambiguation (Han, Giles, Zha, Li, & Tsioutsiouliklis, 2004;Sanyal, Bhowmick, & Das, 2021), self-citations (Schreiber, 2007;Szomszor, Pendlebury, & Adams, 2020), citations meaning (Budi & Yaniasih, 2022), and authors' contribution (Shen & Barabási, 2014). Others advocate for incorporating job-market-based measures in university rankings (Cowan & Rossello, 2018;González-Sauri & Rossello, 2022;Wapman, Zhang, Clauset, & Larremore, 2022). ...
This paper bridges the organisational psychology and the economics of science literature to examine the role of ideology-based psychological contract breach in eliciting mild deviant behaviour in academia. We provide empirical evidence of how the deterioration of academic values related to the diffusion of the “publish or perish” paradigm sparkles copyright violations through Sci-Hub. Based on a representative sample of 2849 academics working in top institutions
in 6 European countries, we find that ideology-based psychological contract breach explains Sci-Hub usage, also when controlling for other trivial motivations. The magnitude of the effect depends on contextual and demographic characteristics. Females, foreign and
tenured scholars are less likely to respond with digital piracy when experiencing a contract breach of academic values. Our results contribute to prevention policy design, highlighting how policies restoring academic values might also address academic piracy.
Much effort has been made in the past decades to citation function classification, but noteworthy issues exist. Annotation difficulty resulted in limited data size, especially for minority classes, and inadequate representativeness of the underlying scientific domains. Concerning algorithmic classification, state-of-the-art deep learning-based methods are flawed by generating a feature vector for the whole citation context (or sentence) and failing to exploit the full realm of citation modelling options. Responding to these issues, this paper studied contextualised citation function classification. Specifically, a large new citation context dataset was created by merging and re-annotating six datasets about computational linguistics. A variety of strong SciBERT-based citation function classification models were proposed, and new states of the art were achieved. Through deeper performance analysis, this study focused on answering several research questions about the effective ways of performing citation function classification. More specifically, the study justified the necessity of modelling in-text citations in context and confirmed the superiority of doing citation function classification at citation (segment) level. A particular emphasis was placed on in-depth per-class performance analysis to understand whether citation function classification is robust enough to suit various popular downstream applications and what further efforts are required to meet such analytic needs. Finally, a naïve ensemble classifier was proposed, which greatly improved citation function classification performance.
The primary objective of this research is to create a multi-output classification model for sentiment analysis through the combination of 10 algorithms: BernoulliNB, Decision Tree, K-nearest neighbor, Logistic Regression, LinearSVC, Bagging, Stacking, Random Forest, AdaBoost, and ExtraTrees. In doing so, we aim to identify the optimal algorithm performance and role within the model. The data utilized in this study is derived from customer reviews of cryptocurrencies in Indonesia. Our results indicate that LinearSVC and Stacking exhibit a high accuracy (90%) compared to the other eight algorithms. The resulting multi-output model demonstrates an average accuracy of 88%, which can be considered satisfactory. This research endeavors to innovate in adaptive sentiment analysis classification by developing a multi-output model that utilizes a combination of 10 classification algorithms.
