Determining Sentiment in Citation Text and Analyzing Its Impact on the Proposed Ranking Index

Abstract

Whenever human beings interact with each other, they exchange or express opinions, emotions and sentiments. These opinions can be expressed in text, speech or images. Analysis of these sentiments is one of the popular research areas of present day researchers. Sentiment analysis, also known as opinion mining tries to identify or classify these sentiments or opinions into two broad categoriespositive and negative. Much work on sentiment analysis has been done on social media conversations, blog posts, newspaper articles and various narrative texts. However, when it came to identifying emotions from scientific papers, researchers used to face difficulties due to the implicit and hidden natures of opinions or emotions. As the citation instances are considered inherently positive in emotion, popular ranking and indexing paradigms often neglect the opinion present while citing. Therefore in the present paper, we deployed a system of citation sentiment analysis to achieve three major objectives. First, we identified sentiments in the citation text and assigned a score to each of the instances. We have used a supervised classifier for this purpose. Secondly, we have proposed a new index (we shall refer to it hereafter as M-index) which takes into account both the quantitative and qualitative factors while scoring a paper. Finally, we developed a ranking of research papers based on the M-index. We have also shown the impacts of M-index on the ranking of scientific papers.

Modeling the co-citation dependence on semantic layers of co-cited documents

“…The content-based sentiment citation analysis has provided more insights about the ability of sentiments in identifying important citations (Aljuaid et al , 2020) and prestigious articles (i.e. Nobel-laureates-authored articles) (Yan et al ., 2020), improving traditional machine learning approaches for classification (Kilicoglu et al ., 2019) and ranking scientific papers (Gosh et al ., 2018). By analyzing the subjective contents of co-citances, Yaghtin et al (2019b) proposed a new feature called CO-OP.…”

“…the content-based sentiment citation analysis, as a special area in NLP that has so far yielded fruitful results in improving classification and ranking of papers and identifying related and important documents (see, e.g. Aljuaid et al , 2020; Yan et al ., 2020; Kilicoglu et al ., 2019; Gosh et al ., 2018; Jia, 2018). By analyzing the opinions uttered in the co-citances, a new feature called co-opinionatedness (CO-OP) has been recently discovered by Yaghtin et al (2019b).…”

Citation recommendation: approaches and datasets

“…The citation function can be determined-to some degree automaticallyby analyzing the citation context and by extracting features [117,154,155]. Similar tasks to the citation function determination are the polarity determination (i.e., if the author speaks in a positive, neutral, or negative way about the cited paper) [1,61] and the determination of the citation importance [36,160].…”

Citation Recommendation: Approaches and Datasets

“…The citation function can be determined -to some degree automatically -by analyzing the citation context and by extracting features [148,111,147]. Similar tasks to the citation function determination are the polarity determination (i.e., if the author speaks in a positive, neutral, or negative way about the cited paper) [1,57] and the determination of the citation importance [152,35].…”