Purpose： This study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences in the original articles.Design/methodology/approach： ...Purpose： This study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences in the original articles.Design/methodology/approach： Firstly, we apply LDA to analyse topic distribution of citation content. Secondly, in CitationAS, we use bisecting K-means, Lingo and STC to cluster retrieved citation content. Then Word2Vec, Word Net and combination of them are applied to generate cluster labels. Next, we employ TF-IDF, MMR, as well as considering sentence location information, to extract important sentences, which are used to generate surveys. Finally, we adopt manual evaluation for the generated surveys.Findings： In experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-Word Net and bisecting K-means-Word2Vec have better clustering effects. In 5 points evaluation system, survey quality scores obtained by designing methods are close to 3, indicating surveys are within acceptable limits. When considering sentence location information, survey quality will be improved. Combination of Lingo, Word2Vec, TF-IDF or MMR can acquire higher survey quality.Research limitations： The manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and Word Net that may not bring out their strengths. The generated surveys may not contain some newly created knowledge of some articles which may concentrate on sentences with no citing.Practical implications： CitationAS tool can automatically generate a comprehensive, detailed and accurate survey according to user’s search terms. It can also help researchers learn about research status in a certain field.Originality/value： Citaiton AS tool is of practicability. It merges cluster labels from semantic level to improve clustering results. The tool also considers sentence location information when calculating sentence score by TF-IDF and MMR.展开更多
The art of constructing an insightful literature review manuscript has witnessed an exemplar in the work of Oz et al(2023),wherein concept progression harmoniously merges with figures and tables.Reflecting on retrospe...The art of constructing an insightful literature review manuscript has witnessed an exemplar in the work of Oz et al(2023),wherein concept progression harmoniously merges with figures and tables.Reflecting on retrospective data science,it is evident that well-cited articles can wield a transformative influence on the Journal Citation Reports Impact Factor score,as exemplified by Robert Weinberg’s landmark on cancer(Hanahan and Weinberg,2011).Here,we aim to spotlight a commendable contribution by Tuba Oz,Ajeet Kaushik,and Małgorzata Kujawska in this issue while pivoting towards identifying the hallmarks of a subpar literature review-elements that hinder rather than promote advancement.The hurdles and roadblocks encountered within subpar literature reviews are multifold.Anticipation of emerging trends,identification of challenges,and exploration of solutions remain conspicuously absent.Original Contributions fail to surface amidst the vast sea of pre-existing literature,with noticeable gaps amplified by the lack of illustrative figures and tables.The manuscript,at times,assumes a skeletal form,reflecting an attempt to accommodate an excess of references,leading to convoluted sentences laden with citations.In contrast,a potent solution lies in adopting a comprehensive approach.A nuanced and critical evaluation of sources can culminate in a robust discussion,surpassing the mere summarization of conclusions drawn by others.This approach,often dismissed,holds the potential to elevate clarity,coherence,and logical flow,ultimately inviting engaged readership and coveted citations.The critical necessity of integrating visionary insights is underscored and achieved through a rigorous analysis of pivotal concepts and innovative ideas.Examples can be harnessed to elucidate the application of these solutions.We advocate a paradigm shift,urging literature review writers to embrace the readers’perspective.A literature review’s purpose extends beyond providing a comprehensive panorama;it should illuminate avenues for concept development within a specific field of interest.By achieving this balance,literature reviews stand to captivate a devoted readership,paving the way for manuscripts that are both widely read and frequently cited.The pathway forward requires a fusion of astute analysis and visionary insights,shaping the future of literature review composition.展开更多
基金supported by Major Projects of National Social Science Fund (No. 17ZDA291)Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) (No. MJUKF201704)Qing Lan Project
文摘Purpose： This study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences in the original articles.Design/methodology/approach： Firstly, we apply LDA to analyse topic distribution of citation content. Secondly, in CitationAS, we use bisecting K-means, Lingo and STC to cluster retrieved citation content. Then Word2Vec, Word Net and combination of them are applied to generate cluster labels. Next, we employ TF-IDF, MMR, as well as considering sentence location information, to extract important sentences, which are used to generate surveys. Finally, we adopt manual evaluation for the generated surveys.Findings： In experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-Word Net and bisecting K-means-Word2Vec have better clustering effects. In 5 points evaluation system, survey quality scores obtained by designing methods are close to 3, indicating surveys are within acceptable limits. When considering sentence location information, survey quality will be improved. Combination of Lingo, Word2Vec, TF-IDF or MMR can acquire higher survey quality.Research limitations： The manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and Word Net that may not bring out their strengths. The generated surveys may not contain some newly created knowledge of some articles which may concentrate on sentences with no citing.Practical implications： CitationAS tool can automatically generate a comprehensive, detailed and accurate survey according to user’s search terms. It can also help researchers learn about research status in a certain field.Originality/value： Citaiton AS tool is of practicability. It merges cluster labels from semantic level to improve clustering results. The tool also considers sentence location information when calculating sentence score by TF-IDF and MMR.
文摘The art of constructing an insightful literature review manuscript has witnessed an exemplar in the work of Oz et al(2023),wherein concept progression harmoniously merges with figures and tables.Reflecting on retrospective data science,it is evident that well-cited articles can wield a transformative influence on the Journal Citation Reports Impact Factor score,as exemplified by Robert Weinberg’s landmark on cancer(Hanahan and Weinberg,2011).Here,we aim to spotlight a commendable contribution by Tuba Oz,Ajeet Kaushik,and Małgorzata Kujawska in this issue while pivoting towards identifying the hallmarks of a subpar literature review-elements that hinder rather than promote advancement.The hurdles and roadblocks encountered within subpar literature reviews are multifold.Anticipation of emerging trends,identification of challenges,and exploration of solutions remain conspicuously absent.Original Contributions fail to surface amidst the vast sea of pre-existing literature,with noticeable gaps amplified by the lack of illustrative figures and tables.The manuscript,at times,assumes a skeletal form,reflecting an attempt to accommodate an excess of references,leading to convoluted sentences laden with citations.In contrast,a potent solution lies in adopting a comprehensive approach.A nuanced and critical evaluation of sources can culminate in a robust discussion,surpassing the mere summarization of conclusions drawn by others.This approach,often dismissed,holds the potential to elevate clarity,coherence,and logical flow,ultimately inviting engaged readership and coveted citations.The critical necessity of integrating visionary insights is underscored and achieved through a rigorous analysis of pivotal concepts and innovative ideas.Examples can be harnessed to elucidate the application of these solutions.We advocate a paradigm shift,urging literature review writers to embrace the readers’perspective.A literature review’s purpose extends beyond providing a comprehensive panorama;it should illuminate avenues for concept development within a specific field of interest.By achieving this balance,literature reviews stand to captivate a devoted readership,paving the way for manuscripts that are both widely read and frequently cited.The pathway forward requires a fusion of astute analysis and visionary insights,shaping the future of literature review composition.
