<abstract xmlns="http://www.w3.org/1999/xhtml"><sec id="j_jdis-2018-0007_s_007_w2aab3b7b2b1b6b1aab1c18b1Aa"><h3>Purpose</h3><p>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.</p></sec><sec id="j_jdis-2018-0007_s_008_w2aab3b7b2b1b6b1aab1c18b2Aa"><h3>Design/methodology/approach</h3><p>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, WordNet 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.</p></sec><sec id="j_jdis-2018-0007_s_009_w2aab3b7b2b1b6b1aab1c18b3Aa"><h3>Findings</h3><p>In experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-WordNet 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.</p></sec><sec id="j_jdis-2018-0007_s_010_w2aab3b7b2b1b6b1aab1c18b4Aa"><h3>Research limitations</h3><p>The manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and WordNet 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.</p></sec><sec id="j_jdis-2018-0007_s_011_w2aab3b7b2b1b6b1aab1c18b5Aa"><h3>Practical implications</h3><p>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.</p></sec><sec id="j_jdis-2018-0007_s_012_w2aab3b7b2b1b6b1aab1c18b6Aa"><h3>Originality/value</h3><p>CitaitonAS 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.</p></sec></abstract>

PurposeThis 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/approachFirstly, 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, WordNet 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.FindingsIn experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-WordNet 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 limitationsThe manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and WordNet 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 implicationsCitationAS 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/valueCitaitonAS 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.

CitationAS: A Tool of Automatic Survey Generation Based on Citation Content

Nanjing University of Science and Technology

Journal of Data and Information Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"CitationAS: A Tool of Automatic Survey Generation Based on Citation Content"}

PurposeThis study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences...

CitationAS: A Tool of Automatic Survey Generation Based on Citation Content

Article Category: Research Paper

Publié en ligne: 22 juin 2018

Pages: 20 - 37

Reçu: 17 déc. 2017

Accepté: 08 mai 2018

DOI: https://doi.org/10.2478/jdis-2018-0007

Mots clés
Automatic survey system, Citation content, Clustering algorithms, Label generation approaches, Sentence extraction methods

© 2018 Walter de Gruyter GmbH, Berlin/Boston, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

CitationAS: A Tool of Automatic Survey Generation Based on Citation Content

Article Category: Research Paper

Publié en ligne: 22 juin 2018

Pages: 20 - 37

Reçu: 17 déc. 2017

Accepté: 08 mai 2018

DOI: https://doi.org/10.2478/jdis-2018-0007

Mots clésAutomatic survey system, Citation content, Clustering algorithms, Label generation approaches, Sentence extraction methods

© 2018 Walter de Gruyter GmbH, Berlin/Boston, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Mots clés
Automatic survey system, Citation content, Clustering algorithms, Label generation approaches, Sentence extraction methods