عنوان مقاله [English]
Purpose: The challenges of quantitative citation analysis are believed to be partially answered by the content-based approach, including citance opinion mining. To provide further research evidence, the present study investigated the correlation between the results of these two approaches.
Methodology: Using citation analysis method with the quantitative and opinion mining approaches, this communication explored a sample of medical papers. Bibliographic, citance and opinion data were extracted from PubMed, CoLil and SentiWords, respectively. The citances were processed using KNIME. The data were analyzed by Spearman Correlation.
Findings: The citances carried numerous opinionated words. The citation counts were directly correlated to the absolute frequency of the opinionated citances, but indirectly correlated to their relative frequency. Furthermore, they had an insignificant correlation with the relative frequency of positive contexts, while displaying significant direct relationships with negative and neutral ones. Moreover, they are indirectly associated with the average opinion scores.
Conclusion: As citation counts increase, the cited papers witness a reduction in their opinionated contexts’ relative numbers, while experiencing an increase in their negative and neutral ones’. Consequently, it is necessary to apply the content-based citation analysis to adjust the results of the quantitative approach.