Predicting literature’s early impact with sentiment analysis in Twitter

Abstract

The traditional bibliometric techniques gauge the research impact through citation-based quantitative indices. However, due to citation lag time, it may take years to address the impact of an article. This paper seeks to measure an early impact of research articles using tweet sentiments associated with them. We claim that the papers cited in positive and neutral tweets have a higher impact than those not cited or cited in negative tweets. Accordingly, we use SentiStrenth, and we improve it by incorporating new opinion bearing words of scientific domain in its sentiment lexicons. Then, we classify the sentiment of 6,482,260 tweets linked to 1,083,535 publications covered by Altmetric.com. By using positive and negative tweets as an independent variable and the citation count as the dependent variable, the linear regression analysis shows a weak positive prediction of high citation counts across 16 broad disciplines in Scopus. By introducing an additional indicator, i.e. 'number of unique Twitter users,' the regression model improves the adjusted R-squared value of regression analysis in several disciplines. Overall, the encouraging positive correlation between the tweet sentiments and citations show that Twitterbased opinion may be exploited as a complementary indicator for predicting literature's early impact.

Sentiment analysis and its applications in fighting COVID-19 and infectious diseases: A systematic review

“…Sentiment analysis contributes to the understanding of human emotions as it can seek people’s behaviours as users engage in these social media applications ( Ji, et al, 2016 ). Additionally, these media applications have been employed in various application domains, including tourism ( Ainin, Feizollah, Anuar, & Abdullah, 2020 ), business ( Reyes-Menendez, Saura, & Filipe, 2020 ), education ( Hassan, et al, 2020 ) and health (Rodrigues, das Dores, Camilo-Junior, & Rosa, 2016), for various beneficial purposes, such as analysing opinions ( Zarrad, et al, 2014 ) and allowing people to express their emotions freely ( Chung, et al, 2015 ), and for highly dynamic and real-time data trends ( Chaudhary & Naaz, 2017 ). With this feature, large-scale communities can be observed at a low cost ( Choi, et al, 2017 ).…”

$CAG$ : Stylometric Authorship Attribution of Multi-Author Documents Using a Co-Authorship Graph

“…For single-label classification tasks, each instance in the training data is associated with one class label ''l'' from a disjoint label set L [38], [39]. When |L| = 2, a learning problem is known as binary classification problem (e.g., the gender identification problem, where the task is to assign an anonymous text to one of two classes, i.e., male or female) [40], [41].…”

Microbiome Research: Open Communication Today, Microbiome Applications in the Future

“…An active engagement in science communication by researchers that goes beyond scientific publications and conference presentations is starting to provide tangible positive outcomes for individuals. For instance, “tweetations” (scientific publications that are being discussed on Twitter) with a positive sentiment can increase downloads and view metrics of scientific publications in the short term and citation rate in the long term [ 50 , 51 ].…”