[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125937-en":3,"doc-seo-125937-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125937,2336474459895,"Aria","https://ap-avatar.wpscdn.com/avatar/22000baeef7a5ed0655?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786071322749376916",8,"Research & Report","Forecasting Publications’ Success Using Machine Learning Prediction Models - Paper","Measuring the success and impact of scientific publications remains controversial, with citation counts widely used as a popular proxy. This paper applies a machine learning framework to test whether alternative metrics (altmetrics) can predict future impact as reflected in later citation counts. The study extracts 7,588 papers from 10 computer science journals and evaluates 14 altmetric indices with variance threshold, Pearson correlation, and mutual information for feature selection. Decision Tree, Random Forest, and SVM classifiers show that altmetrics can forecast future citations, led by social media counts, tweets, news counts, captures, and full-text views, with Random Forest performing best.","Forecasting Publications’ Success Using Machine Learning Prediction Models  \nRand Alchokr1,∗ , Rayed Haider3,∗ , Yusra Shakeel1,2,∗ , Thomas Leich3,4, Gunter Saake1 and Jacob Krüger5  \n1 Otto-von-Guericke University, Magdeburg, Germany 2 Karlsruhe Institute of Technology, Karlsruhe, Germany  \n3 Hochschule Harz, Wernigerode, Germany 4 METOP GmbH, Magdeburg, Germany  \n5 Eindhoven University of Technology, The Netherlands  \nAbstract  \nMeasuring the success and impact of a scientific publication is an important, thus controversial matter. Despite all the criticism, it is widespread that citation counts is considered a popular indication of a publication‘s success. Therefore, in this paper, we use a machine learning framework to test the ability of alternative metrics (altmetrics) to predict the future impact of papers reflected in the citation counts. To achieve the experiment, we extracted 7,588 papers from 10 computer science journals. To build the feature space for the prediction problem, 14 different altmetric indices were collected, 3 feature selection approaches, namely, Variance threshold, Pearson’s Correlation, and Mutual information method, were used to minimize the feature space and rank the features according to their contribution to the original dataset. To identify the classification performance of these features, three classifiers were used: Decision Tree, Random Forest, and Support Vector Machines. According to the experimental data, altmetrics can predict future citations and the most useful altmetrics indications are social media count, tweets, news count, capture count, and full-text view, with Random Forest outperforming the other classifiers.  \nKeywords  \nBibliometric, alternative metrics, machine learning, computer science  \n1. Introduction  \nA successful publication is a desirable goal for any researcher, irrespective of their scientific field. However, judging how successful a published paper is and measuring that success is considered a critical issue. Furthermore, forecasting scientific impact and success is becoming an essential regular task for the hiring committees, funding agencies, and department heads for recruitment decisions and rewards [3, 7, 26] . Through this a merit-based career advancement scheme is developed, that forecasts the individual’s performance based on past achievements and projects future performance. However, distilling the contents of each article into an appraisal  \nBIR 2023: 13th International Workshop on Bibliometric-enhanced Information Retrieval at ECIR 2023, April 2, 2023 ∗Corresponding author.  \n[Envelope-Open](Envelope-Open rand.alchokr@ovgu.de)[ rand.alchokr@ovgu.de](Envelope-Open rand.alchokr@ovgu.de) (R. Alchokr); [rayedhaider95@gmail.com](rayedhaider95@gmail.com) (R. Haider); [yusra.shakeel@kit.edu](yusra.shakeel@kit.edu) (Y. Shakeel);  \n[tleich@hs-harz.de](tleich@hs-harz.de) (T. Leich); [saake@ovgu.de](saake@ovgu.de) (G. Saake); [j.kruger@tue.nl](j.kruger@tue.nl) (J. Krüger)  \nOrcid 0000−0003−0112−5430 (R. Alchokr); 0000-0001-5135-4325 (Y. Shakeel); 0000-0001-9580-7728 (T. Leich);  \n0000-0001-9576-8474 (G. Saake); 0000-0002-0283-248X (J. Krüger)  \n © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) . CWPEURorkroceshopedings http://ceurISSN 1613-ws-0073.org CEUR Workshop Proceedings ([CEUR-WS.org](CEUR-WS.org))  \n77  \nCEUR ceur-ws.org  \nWorkshop ISSN 1613-0073 Proceedings   \nof an individual’s past, present, and future influence and determining an acceptable ranking of candidates is significantly challenging when presented with candidate pools ranging from a few hundred for tenure-track positions to thousands for fellowship and grant competitions.  \nIn the past decades, researchers have relied heavily on quantitative indicators for evaluating the scientific success of a given research body. Citation frequency is a well-known criterion for research evaluation and despite all the criticis","cbCaimm16YQtAL16","https://ap.wps.com/l/cbCaimm16YQtAL16","pdf",385533,7,1,13,"English","en",105,"# Abstract\n# Keywords\n# Introduction\n## Measuring publication success and impact\n## Bibliometrics vs. altmetrics\n## Machine learning approaches for forecasting","[{\"question\":\"Why do the authors focus on citation counts and altmetrics for publication success prediction?\",\"answer\":\"Citation counts are commonly used to indicate success, but their adequacy is debated. The study investigates whether altmetrics collected from online platforms can better or additionally predict future impact measured through citations.\"},{\"question\":\"What data and features are used to build the prediction models?\",\"answer\":\"The experiment uses 7,588 papers from 10 computer science journals. Feature construction relies on 14 different altmetric indices, followed by feature selection using variance threshold, Pearson’s correlation, and mutual information.\"},{\"question\":\"Which classifiers and altmetric indicators show the strongest predictive performance?\",\"answer\":\"The classifiers include Decision Tree, Random Forest, and Support Vector Machines. The results indicate that social media count, tweets, news count, capture count, and full-text view are the most useful altmetrics, and Random Forest outperforms the other classifiers.\"}]","Forecasting Publications’ Success Using Machine Learning Prediction Models - Paper | PDF",1785902124,33,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"forecasting-publications-success-using-machine-learning-prediction-models-paper","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/forecasting-publications-success-using-machine-learning-prediction-models-paper/125937/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why do the authors focus on citation counts and altmetrics for publication success prediction?","Question",{"text":77,"@type":78},"Citation counts are commonly used to indicate success, but their adequacy is debated. The study investigates whether altmetrics collected from online platforms can better or additionally predict future impact measured through citations.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What data and features are used to build the prediction models?",{"text":82,"@type":78},"The experiment uses 7,588 papers from 10 computer science journals. Feature construction relies on 14 different altmetric indices, followed by feature selection using variance threshold, Pearson’s correlation, and mutual information.",{"name":84,"@type":75,"acceptedAnswer":85},"Which classifiers and altmetric indicators show the strongest predictive performance?",{"text":86,"@type":78},"The classifiers include Decision Tree, Random Forest, and Support Vector Machines. The results indicate that social media count, tweets, news count, capture count, and full-text view are the most useful altmetrics, and Random Forest outperforms the other classifiers.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]