Türk Kütüphaneciliği Dergisi Dijital Arşivindeki Bilimsel Makalelere Erişimin Artırılması: Türkçe Özlerden Anahtar Kelimeler Atanması

Yıl 2024, Cilt: 38 Sayı: 4, 205 - 224

Kemal Yayla

https://doi.org/10.24146/tk.1487124

Öz

Amaç: Bu çalışmanın amacı, Türk Kütüphaneciliği dergisinin web sitesinde yer alan ve anahtar kelime ataması yapılmamış hakemli makalelere Türkçe özlerini kullanarak anahtar kelime atamaları gerçekleştirmektir. Bu sayede anahtar kelime eksikliği nedeniyle erişimde güçlük çekilen web arşivindeki çalışmalara daha etkin bir şekilde erişim sağlanması hedeflenmektedir.

Yöntem: Çalışmada, 1995 ile 1999 yılları arasında anahtar kelime olmaksızın yayımlanmış olan 58 hakemli makale incelenmiştir. Anahtar kelime ataması için Türkçe özleri girdi olarak kullanılan YAKE algoritması kullanılmış, metinlerin işlenmesi için Zemberek doğal dil işleme aracı ve Python programlama dili tercih edilmiştir. Atanan anahtar kelimelerin anlamlılığı, Anlamlılık Kontrol Oranı (AKO) ve Ortalama Mutlak Hata (OMH) değerleri ile ölçülmüştür. Atanan anahtar kelimelerin bağlamsal geçerliliği üç uzman değerlendirici ile algoritmanın atadığı anahtar kelimeler arasında değerlendirici uyumunu ölçen AC1 oranı ile ölçülmüştür.

Bulgular: Anahtar kelime ataması yapılan makalelerde en sık atama yapılan kelimelerin “kütüphane”, “bilgi”, “hizmet” ve “makale” olduğu tespit edilmiştir. Algoritmanın OMH değeri 0,099 olarak belirlenmiş, bu da algoritmanın yüksek doğrulukla anahtar kelime atadığını göstermektedir. Ancak, uzman değerlendiriciler ile algoritma tarafından atanan anahtar kelimeler arasında düşük seviyede uyum tespit edilmiştir.

Sonuç: Çalışma, Türkçe özlerden anahtar kelime çıkarımı yapmanın dijital belge erişimini artırmada önemli bir yöntem olduğunu göstermektedir. Algoritmaların daha yüksek performans göstermesi için, uzmanlar tarafından belirlenen veri setleri ile eğitilmeleri gerekmektedir. Ayrıca, yapılandırılmış öz kullanımı ve öz metinlerin uzunluğunun artırılması önerilmektedir.

Özgünlük: Bu çalışma bilimsel makalelerin Türkçe özlerden anahtar kelime çıkarımı yaparak dijital belge erişimini artırmaya yönelik özgün bir yaklaşım sunmaktadır. Kütüphanecilik ve Bilgi Bilim alanındaki dijitalleşmiş makaleleri web ortamından erişimin arttırılmasına yönelik yapılan ilk çalışmalardan biridir.

Anahtar Kelimeler

Anahtar kelime ataması, YAKE, Türkçe öz, dijital arşiv

Etik Beyan

Çalışma etik kurul izni gerektirmeyen çalışmalar kapsamında yer almaktadır.

Teşekkür

Çalışma kapsamında uzman değerlendirici olarak yer alan Kütüphaneci Dilan Karataş, Kütüphaneci Tuğba As ve Kütüphane Müdürü Fatih Furkan Gebel'e teşekkür ederim.

Enhancing Access to Scientific Articles in the Turkish Librarianship Journal Digital Archive: Assigning Keywords from Turkish Abstracts

Öz

Purpose: This study aims to assign keywords to peer-reviewed articles on the Turkish Librarianship Journal's website that do not have keyword assignments by using their Turkish abstracts. The goal is to improve access to works in the web archive that are difficult to reach due to the lack of keywords.

Method: The study examined 58 peer-reviewed articles published without keywords between 1995 and 1999. The YAKE algorithm was used for keyword assignment, with Turkish abstracts as input, and the Zemberek natural language processing tool and Python programming language were utilized for text processing. The meaningfulness of the assigned keywords was measured using the Significance Control Ratio (SCR) and Mean Absolute Error (MAE) values. The contextual validity of the assigned keywords was assessed by measuring the inter-rater agreement (AC1 ratio) between three expert evaluators and the algorithm-assigned keywords.

Findings: The most frequently assigned keywords in the articles were "library," "information," "service," and "article." The algorithm's MAE value was determined to be 0.099, indicating that the algorithm assigned keywords with high accuracy. However, low agreement was found between the keywords the experts assigned and those the algorithm assigned.

Implications: The study demonstrates that extracting keywords from Turkish abstracts is essential for enhancing access to digital documents. Algorithms need to be trained on datasets determined by experts to perform better. Additionally, using structured abstracts and increasing the length of abstract texts are recommended.

Originality: This study presents a novel approach to improving digital document access by extracting keywords from Turkish abstracts of scientific articles. It is one of the first studies aimed at increasing web access to digitized articles in the Librarianship and Information Science field.

Anahtar Kelimeler

Keyword assignment, YAKE, Turkish abstract, digital archive

Kaynakça

• Akın, A. A. (2024). Zemberek-NLP: Natural Language Processing tools for Turkish (Versiyon 0.17.1) [Java; Windows]. https://github.com/ahmetaa/zemberek-nlp
• Aldemir, A., ve Oğuz, E. S. (2006). Sayısal dijital kültürün korunması: Web arşivleme. Türk Kütüphaneciliği, 20(3), 283-312. https://dergipark.org.tr/tr/pub/tk/issue/48940/624280
• Alharbi, L. M., ve Swales, J. M. (2011). Arabic and English abstracts in bilingual language science journals: Same or different? Languages in Contrast, 11(1), 70-86. https://doi.org/10.1075/lic.11.1.06alh
• Allen, E. J., ve Weber, R. K. (2015). An exploration of indexed and non-indexed open access journals: Identifying metadata coding variations. Journal of Web Librarianship, 9(2-3), 65-84. https://doi.org/10.1080/19322909.2015.1020185
• An, S., ve Jung, J. J. (2021). A heuristic approach on metadata recommendation for search engine optimization. Concurrency and Computation: Practice and Experience, 33(3), e5407. https://doi.org/10.1002/cpe.5407
• Atanassova, I., Bertin, M., ve Larivière, V. (2016). On the composition of scientific abstracts. Journal of Documentation, 72(4), 636-647. https://doi.org/10.1108/JDOC-09-2015-0111
• Atılgan, D. (2002). Türk Kütüphaneciliği dergisinin yayın yaşamındaki yeri. Türk Kütüphaneciliği, 16(3), 248-256. http://tk.org.tr/index.php/TK/article/view/918/911
• Bayter, M. (2009). Türkçe web sitelerinin kataloglanmasının önemi. Türk Kütüphaneciliği, 23(3), 563-585. https://dergipark.org.tr/en/pub/tk/issue/48915/623745
• Beel, J., Gipp, B., ve Wilde, E. (2010). Academic Search Engine Optimization (ASEO): Optimizing Scholarly Literature for Google Scholar & Co. Journal of Scholarly Publishing, 41(2), 176-190. https://doi.org/10.3138/jsp.41.2.176
• Beliga, S. (2014). Keyword extraction: A review of methods and approaches. University of Rijeka, Department of Informatics, Rijeka, 1(9). http://langnet.uniri.hr/papers/beliga/Beliga_KeywordExtraction_a_review_of_methods_and_approaches.pdf
• Beliga, S., Meštrović, A., ve Martinčić-Ipšić, S. (2016). Selectivity-based keyword extraction method. International Journal on Semantic Web and Information Systems, 12(3), 1-26. https://doi.org/10.4018/IJSWIS.2016070101
• Bhowmik, R. (2008). Keyword extraction from abstracts and titles. IEEE SoutheastCon 2008, 610-617. https://doi.org/10.1109/SECON.2008.4494366
• Binici, K. (2019). Makine öğrenmesi yaklaşımıyla e-belgelere standart dosya plan numaralarının otomatik olarak atanması üzerine bir çalışma. Bilgi Yönetimi, 2(2), 116-126. https://doi.org/10.33721/by.654464
• Bitri, E., ve Keseroğlu, H. S. (2015). Türk Kütüphaneciliği ve Bilgi Dünyası dergilerinin özlerine eleştirel bir bakış. Türk Kütüphaneciliği, 29(2), 241-257. https://dergipark.org.tr/tr/pub/tk/issue/48742/620117
• Blank, I., Rokach, L., ve Shani, G. (2016). Leveraging metadata to recommend keywords for academic papers. Journal of the Association for Information Science and Technology, 67(12), 3073-3091. https://doi.org/10.1002/asi.23571
• Brienza, C. (2012). Opening the wrong gate? The academic spring and scholarly publishing in the humanities and social sciences. Publishing Research Quarterly, 28, 159-171. https://doi.org/10.1007/s12109-012-9272-5
• Campos, R., Mangaravite, V., Pasquali, A., Jorge, A. M., Nunes, C., ve Jatowt, A. (2018). YAKE! Collection-Independent Automatic Keyword Extractor. Içinde G. Pasi, B. Piwowarski, L. Azzopardi, ve A. Hanbury (Ed.), Advances in Information Retrieval (C. 10772, ss. 806-810). Springer International Publishing. https://doi.org/10.1007/978-3-319-76941-7_80
• Campos, R., Mangaravite, V., Pasquali, A., Jorge, A., Nunes, C., ve Jatowt, A. (2020). YAKE! Keyword extraction from single documents using multiple local features. Information Sciences, 509, 257-289. https://doi.org/10.1016/j.ins.2019.09.013 Chamorro-Padial, J., ve Rodríguez-Sánchez, R. (2023). Attention–Survival Score: A Metric to Choose Better Keywords and Improve Visibility of Information. Algorithms, 16(4), 196. https://doi.org/10.3390/a16040196
• Chi, Y., Zhu, J., Huag, L., ve Xu, H. (2019). Concepts recommendation for searching scientific papers. Cluster Computing, 22(S4), 8669-8675. https://doi.org/10.1007/s10586-018-1937-1
• Chmutina, K., Sadler, N., Von Meding, J., ve Abukhalaf, A. H. I. (2020). Lost (and found?) in translation: Key terminology in disaster studies. Disaster Prevention and Management: An International Journal, 30(2), 149-162. https://doi.org/10.1108/DPM-07-2020-0232
• Conway, P. (2015). Digital transformations and the archival nature of surrogates. Archival Science, 15, 51-69. https://doi.org/10.1007/s10502-014-9219-z
• Cutting, D. J. (2012). Vague language in conference abstracts. Journal of English for Academic Purposes, 11(4), 283-293. https://doi.org/10.1016/j.jeap.2012.05.004
• Çapkın, Ç. (2009). Türk kütüphaneciler derneği web hizmetleri: 60. Yıla doğru yeni ufuklara. Türk Kütüphaneciliği, 23(2), 395-398. https://dergipark.org.tr/en/download/article-file/815027
• Çapkın, Ç. (2014). Bilimsel elektronik dergilerin kullanımı: Türk Kütüphaneciliği dergisinin işlem günlüğü analizi. Türk Kütüphaneciliği, 28(3), 308-319. https://dergipark.org.tr/tr/pub/tk/issue/48745/620207
• Daudaravicius, V. (2016). A Framework for Keyphrase Extraction from Scientific Journals. İçinde A. González-Beltrán, F. Osborne, ve S. Peroni (Ed.), Semantics, Analytics, Visualization. Enhancing Scholarly Data (C. 9792, ss. 51-66). Springer International Publishing. https://doi.org/10.1007/978-3-319-53637-8_7
• Dişli, M., ve Tonta, Y. (2023). Veri olarak kültürel miras koleksiyonları. Türk Kütüphaneciliği. https://doi.org/10.24146/tk.1317445
• Dynich, A., ve Wang, Y. (2017). Analysis of novelty of a scientific text as a basis for assessment of efficiency of scientific activities. Journal of Organizational Change Management, 30(5), 668-682. https://doi.org/10.1108/JOCM-10-2016-0226
• Ercan, G., ve Cicekli, I. (2007). Using lexical chains for keyword extraction. Information Processing & Management, 43(6), 1705-1714. https://doi.org/10.1016/j.ipm.2007.01.015
• Erzurumlu, H. Y., ve Akgul, Y. S. (2023). Adaptive keyword extraction service for Turkish. Içinde K. Arai (Ed.), Intelligent Systems and Applications (C. 543, ss. 495-506). Springer International Publishing. https://doi.org/10.1007/978-3-031-16078-3_34
• Escudero, M. P., ve Swales, J. M. (2011). Tracing convergence and divergence in pairs of Spanish and English research article abstracts. Ibérica, 21, 49-70. https://www.redalyc.org/pdf/2870/287023883004.pdf
• Fleiss, J. L., ve Cohen, J. (1973). The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and Psychological Measurement, 33(3), 613-619. https://doi.org/10.1177/001316447303300309
• Gil‐Leiva, I., ve Alonso‐Arroyo, A. (2007). Keywords given by authors of scientific articles in database descriptors. Journal of the American Society for Information Science and Technology, 58(8), 1175-1187. https://doi.org/10.1002/asi.20595
• Gillis, R., Betz, S., Chan, J., Hatherill, J., Jay, S., Kosavic, A., Pritt, A., MacFarland, D., Maistrovskaya, M., Moore, A., Sprout, B., ve Stranack, K. (2019). Getting Found, Staying Found, Increasing Impact. OJS på dansk, 10(9). https://doi.org/10.7146/ojssb.v10i9.116299
• Grey, A., ve Hurko, C. R. (2012). So you think you’re an expert: Keyword searching vs. Controlled subject headings. Codex: The Journal of the Louisiana Chapter of the ACRL, 1(4), 15-26.
• Gwet, K. L. (2008). Computing inter‐rater reliability and its variance in the presence of high agreement. British Journal of Mathematical and Statistical Psychology, 61(1), 29-48. https://doi.org/10.1348/000711006X126600
• Gwet, K. L. (2019). irrCAC: Computing Chance-Corrected Agreement Coefficients (CAC) (Versiyon 1.0) [R; Windows]. https://CRAN.R-project.org/package=irrCAC
• Hahs-Vaughn, D. L., ve Onwuegbuzie, A. J. (2010). Quality of abstracts in articles submitted to a scholarly journal: A mixed methods case study of the journal Research in the Schools. Library & Information Science Research, 32(1), 53-61. https://doi.org/10.1016/j.lisr.2009.08.004
• Hartley, J. (2016). What’s new in abstracts of science articles? Journal of the Medical Library Association, 104(3), 235-236. https://doi.org/10.3163/1536-5050.104.3.011
• Hartley, J., ve Cabanac, G. (2017). Thirteen ways to write an abstract. Publications, 5(2), 11. https://doi.org/10.3390/publications5020011
• Hartley, J., ve Kostoff, R. N. (2003). How Useful are `Key Words’ in Scientific Journals? Journal of Information Science, 29(5), 433-438. https://doi.org/10.1177/01655515030295008
• Hawking, D., ve Zobel, J. (2007). Does topic metadata help with Web search? Journal of the American Society for Information Science and Technology, 58(5), 613-628. https://doi.org/10.1002/asi.20548
• Honey, S. L. (2005). Preservation of electronic scholarly publishing: An analysis of three approaches. Portal: Libraries and the Academy, 5(1), 59-75. https://doi.org/10.1353/pla.2005.0005
• Howcroft, G. (2007). A Beginner’s Guide to Metadata and Keywords. Editors’ Bulletin, 3(3), 75-77. https://doi.org/10.1080/17521740701788437
• Hyland, K., ve Tse, P. (2005). Hooking the reader: A corpus study of evaluative that in abstracts. English for Specific Purposes, 24(2), 123-139. https://doi.org/10.1016/j.esp.2004.02.002
• Jamar, N., Šauperl, A., ve Bawden, D. (2014). The components of abstracts: The logical structure of abstracts in the areas of materials science and technology and of library and information science. New Library World, 115(1/2), 15-33. https://doi.org/10.1108/NLW-09-2013-0069
• Kaplan, R. B., Cantor, S., Hagstrom, C., Kamhi-Stein, L. D., Shiotani, Y., ve Zimmerman, C. B. (1994). On abstract writing. Text - Interdisciplinary Journal for the Study of Discourse, 14(3). https://doi.org/10.1515/text.1.1994.14.3.401
• Kayaoğlu, H. D. (2007). Elektronik dergi kullanımı ile bilim dalı ilişkisi: Betimleyici bir inceleme. Türk Kütüphaneciliği, 21(4), 440-458. https://dergipark.org.tr/tr/pub/tk/issue/48936/624246
• Koller, W. (1995). The concept of equivalence and the object of translation studies. Target. International Journal of Translation Studies, 7(2), 191-222. https://doi.org/10.1075/target.7.2.02kol
• Küçük, M. E., ve Alır, G. (2003). Dijital koruma (arşivleme) stratejileri ve bazı uygulama örnekleri. Türk Kütüphaneciliği, 17(4), 340-356. http://www.tk.org.tr/index.php/TK/article/view/299/291
• Li, S.-Q., Du, S.-M., ve Xing, X.-Z. (2017). A Keyword Extraction Method for Chinese Scientific Abstracts. Proceedings of the 2017 International Conference on Wireless Communications, Networking and Applications, 133-137. https://doi.org/10.1145/3180496.3180620
• Liu, G., ve Zhai, Z. (2011). Research on keywords Extraction of Chinese documents based on TEXT-NET. 2011 International Conference on Electric Information and Control Engineering, 6074-6077. https://doi.org/10.1109/ICEICE.2011.5777961
• Lu, K., ve Kipp, M. E. I. (2014). Understanding the retrieval effectiveness of collaborative tags and author keywords in different retrieval environments: An experimental study on medical collections. Journal of the Association for Information Science and Technology, 65(3), 483-500. https://doi.org/10.1002/asi.22985
• Lu, W., Huang, S., Yang, J., Bu, Y., Cheng, Q., ve Huang, Y. (2021). Detecting research topic trends by author-defined keyword frequency. Information Processing & Management, 58(4), 102594. https://doi.org/10.1016/j.ipm.2021.102594
• Mahdi Taheri, S., Hariri, N., ve Ramatollah Fattahi, S. (2014). Does discarding XML declarations and changing file extensions improve the indexability and visibility of metadata tag names in web search engines? Journal of Information Science, 40(6), 796-805. https://doi.org/10.1177/0165551514550139
• Mihalcea, R., ve Tarau, P. (2004). Textrank: Bringing order into text. İçinde D. Lin ve D. Wu (Ed.), Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (ss. 404-411). Association for Computational Linguistics. https://web.archive.org/web/20240327095740/https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf
• Mohamed, K. A. F. (2006). The impact of metadata in web resources discovering. Online Information Review, 30(2), 155-167. https://doi.org/10.1108/14684520610659184
• Mohseni, M., ve Faili, H. (2020). Title Generation and Keyphrase Extraction from Persian Scientific Texts. 2020 25th International Computer Conference, Computer Society of Iran (CSICC), 1-6. https://doi.org/10.1109/CSICC49403.2020.9050113
• Morozov, D. A., Glazkova, A. V., Tyutyulnikov, M. A., ve Iomdin, B. L. (2023). Keyphrase Generation for Abstracts of the Russian-Language Scientific Articles. NSU Vestnik. Series: Linguistics and Intercultural Communication, 21(1), 54-66. https://doi.org/10.25205/1818-7935-2023-21-1-54-66
• Moulaison, H. L., ve Million, A. J. (2015). E-publishing in libraries: The [digital] preservation imperative. OCLC Systems & Services: International digital library perspectives, 31(2), 87-98. https://doi.org/10.1108/OCLC-02-2014-0009
• Ooms, J. (2024). hunspell: High-Performance Stemmer, Tokenizer, and Spell Checker (Versiyon 3.03) [R; Windows]. https://docs.ropensci.org/hunspell/ https://ropensci.r-universe.dev/hunspell
• Önal Süzek, T. (2017). Using latent semantic analysis for automated keyword extraction from large document corpora. Turkish Journal of Electrical Engineering & Computer Sciences, 25, 1784-1794. https://doi.org/10.3906/elk-1511-203
• Papagiannopoulou, E., ve Tsoumakas, G. (2020). A review of keyphrase extraction. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(2), e1339. https://doi.org/10.1002/widm.1339
• Rose, S., Engel, D., Cramer, N., ve Cowley, W. (2010). Automatic Keyword Extraction from Individual Documents. Içinde M. W. Berry ve J. Kogan (Ed.), Text Mining (1. bs, ss. 1-20). Wiley. https://doi.org/10.1002/9780470689646.ch1
• Šauperl, A., Klasinc, J., ve Lužar, S. (2008). Components of abstracts: Logical structure of scholarly abstracts in pharmacology, sociology, and linguistics and literature. Journal of the American Society for Information Science and Technology, 59(9), 1420-1432. https://doi.org/10.1002/asi.20858
• Siddiqi, S., ve Sharan, A. (2015). Keyword and Keyphrase Extraction Techniques: A Literature Review. International Journal of Computer Applications, 109(2), 18-23. https://doi.org/10.5120/19161-0607
• Terra, A. L., Agustín Lacruz, C., Bernardes, Ó., Fujita, M. S. L., ve Bueno De La Fuente, G. (2021). Subject-access metadata on ETD supplied by authors: A case study about keywords, titles and abstracts in a Brazilian academic repository. The Journal of Academic Librarianship, 47(1), 102268. https://doi.org/10.1016/j.acalib.2020.102268
• Tonta, Y. (2002). Türk Kütüphaneciliği Dergisi, 1987-2001. Türk Kütüphaneciliği, 16(3), 282-320. http://www.tk.org.tr/index.php/TK/article/view/929/922
• Turney, P. D. (2002). Learning to extract keyphrases from text. arXiv preprint cs/0212013.
• Türk Kütüphaneciliği. (2024). Yazım Kuralları. İçinde Türk Kütüphaneciliği. https://dergipark.org.tr/tr/pub/tk/writing-rules
• Willmott, C., ve Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30, 79-82. https://doi.org/10.3354/cr030079
• Witten, I. H., Paynter, G. W., Frank, E., Gutwin, C., ve Nevill-Manning, C. G. (1999). KEA: Practical automatic keyphrase extraction. Proceedings of the Fourth ACM Conference on Digital Libraries, 254-255. https://doi.org/10.1145/313238.313437
• Yılmaz, Ö., ve Memişoğlu, S. P. (2019). Yükseköğretim kurumlarında akademik performans değerlendirmeye ilişkin akademisyen görüşleri. Yükseköğretim ve Bilim Dergisi, 3, 542-554. https://dergipark.org.tr/tr/pub/higheredusci/issue/61500/918358
• Zhang, C., ve Liu, X. (2011). Review of James Hartley’s research on structured abstracts. Journal of Information Science, 37(6), 570-576. https://doi.org/10.1177/0165551511420217
• Zhang, C., Wang, H., Liu, Y., Wu, D., Liao, Y., ve Wang, B. (2008). Automatic keyword extraction from documents using conditional random fields. Journal of Computational Information Systems, 4(3), 1169-1180. https://core.ac.uk/download/pdf/290479356.pdf
• Zhang, C., Zhao, L., Zhao, M., ve Zhang, Y. (2022). Enhancing keyphrase extraction from academic articles with their reference information. Scientometrics, 127(2), 703-731. https://doi.org/10.1007/s11192-021-04230-4
• Zhang, J., ve Dimitroff, A. (2005). The impact of metadata implementation on webpage visibility in search engine results (Part II). Information Processing & Management, 41(3), 691-715. https://doi.org/10.1016/j.ipm.2003.12.002
• Zhang, J., Yu, Q., Zheng, F., Long, C., Lu, Z., ve Duan, Z. (2016). Comparing keywords plus of WOS and author keywords: A case study of patient adherence research. Journal of the Association for Information Science and Technology, 67(4), 967-972. https://doi.org/10.1002/asi.23437