[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-203785-105":3,"detail-sidebar-cat-0-en-105":80,"doc-detail-203785-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","a-survey-on-recent-approaches-to-question-difficulty-estimation-from-text","A survey on recent approaches to question difficulty estimation from text","","Question Difficulty Estimation (QDE), also known as question calibration, estimates a numerical or categorical difficulty value for educational questions. The work introduces the research field, explains why accurate difficulty estimates matter for student assessment and adaptive testing, and contrasts manual calibration and pretesting with newer NLP-driven approaches. It builds a taxonomy from question characteristics and reviews recent methods, highlighting opportunities for further research and serving as a reference for researchers and practitioners.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-survey-on-recent-approaches-to-question-difficulty-estimation-from-text/203785/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-survey-on-recent-approaches-to-question-difficulty-estimation-from-text/203785.png","ImageObject",300,407,{"name":42,"@type":43},"Sage","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-04","2026-09-04",true,{"@type":52,"interactionType":53,"userInteractionCount":30},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"What is question difficulty estimation (QDE) in educational settings?","Question",{"text":62,"@type":63},"QDE estimates a numerical or categorical value representing a question’s difficulty for educational use. It supports calibration needed for effective testing and student evaluation.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"Why is accurate question difficulty calibration important?",{"text":67,"@type":63},"Miscalibrated questions can present inappropriate difficulty levels, harming learning outcomes and reducing the accuracy of student skill assessment. Tests that are too easy or too hard also produce uninformative score ranges.",{"name":69,"@type":60,"acceptedAnswer":70},"How do traditional approaches like manual calibration and pretesting differ from text-based QDET?",{"text":71,"@type":63},"Manual calibration relies on experts assigning difficulty values, which is subjective and not scalable. Pretesting administers new items without scoring them, then uses responses to calibrate later, but it introduces delays and exposure risks. Text-based QDET uses question text with NLP to estimate difficulty automatically, reducing dependence on pretesting and manual labeling.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},203785,1788563850,{"code":4,"msg":81,"data":82},"success",[83,87,91,95,100,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":84,"show_sort_weight":85,"slug":86},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":88,"show_sort_weight":89,"slug":90},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":92,"show_sort_weight":93,"slug":94},"Exam",70,"exam",{"id":96,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},5,"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":96,"slug":129},19,"General","general",{"code":4,"msg":81,"data":131},{"doc_id":78,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":30,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":79,"read_time":144},687197207057,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","1  \n2  \n3  \n4  \n5  \n6  \n7  \n8  \n9  \n10  \n11  \n12  \n13  \n14  \n15  \n16  \n17  \n18  \n19  \n20  \n21  \n22  \n23  \n24  \n25  \n26  \n27  \n28  \n29  \n30  \n31  \n32  \n33  \n34  \n35  \n36  \n37  \n38  \n39  \n40  \n41  \n42  \n43  \n44  \n45  \n46  \n47  \n48  \n49  \n50  \n51  \n52  \nA survey on recent approaches to question difficulty estimation from text  \nLUCA BENEDETTO and PAOLO CREMONESI, Politecnico di Milano, Italy  \nANDREW CAINES and PAULA BUTTERY, Computer Laboratory & ALTA Inst., University of Cambridge, U.K. ANDREA CAPPELLI, ANDREA GIUSSANI, and ROBERTO TURRIN, Cloud Academy Sagl., Switzerland  \nQuestion Difficulty Estimation from Text (QDET) is the application of Natural Language Processing techniques to the estimation of a value, either numerical or categorical, which represents the difficulty of questions in educational settings. We give an introduction to the field, build a taxonomy based on question characteristics, and present the various approaches that have been proposed in recent years, outlining opportunities for further research. This survey provides an introduction for researchers and practitioners into the domain of question difficulty estimation from text, and acts as a point of reference about recent research in this topic to date.  \nCCS Concepts: • Computing methodologies → Natural language processing; Machine learning; • Applied computing → Education; • General and reference → Surveys and overviews.  \nAdditional Key Words and Phrases: question difficulty estimation, question calibration, student assessment  \nACM Reference Format:  \nLuca Benedetto, Paolo Cremonesi, Andrew Caines, Paula Buttery, Andrea Cappelli, Andrea Giussani, and Roberto Turrin. 2018. A survey on recent approaches to question difficulty estimation from text. In Woodstock ’18: ACM Symposium on Neural Gaze Detection, June 03–05, 2018, Woodstock, NY. ACM, New York, NY, USA, 35 pages. [https://doi.org/10.1145/1122445.1122456](https://doi.org/10.1145/1122445.1122456)  \n1 INTRODUCTION  \nQuestion Difficulty Estimation (QDE)– also referred to as “question calibration” – consists of estimating a value, either numerical or categorical, representing the difficulty of a question, and is of crucial importance in the educational domain. The best way to intuitively understand the importance of an accurate estimation of question difficulty is through some use cases. An example is Computerized Adaptive Testing [62], an examination format in which the students are provided with questions whose difficulty is targeted to their proficiency, that was shown to be highly beneficial to the learning outcome [18] . In case of miscalibrated questions (i.e., whose difficulty has been erroneously estimated), students are provided with questions inappropriate to their level, which affects the learning outcome [108] . Another example is the fact that question difficulty is leveraged for accurately assessing students: indeed, in some testing frameworks, students’skill levels are estimated based on their past answers to exam questions and the known difficulty of those questions. A student which correctly answered a very difficult question will have an estimated knowledge level higher than the oneof a student who correctly answered a lower difficulty question; therefore, miscalibrated items may affect the accuracy of students’ assessment. Lastly, regardless of the testing theory that is used in designing the exams, a test that is too easy or too difficult for a particular group results in a limited range of scores, which is not informative [3] .  \nTraditionally, QDE is performed with either i) manual calibration [1] or ii) pretesting [58] . Manual calibration consists of having one (or more) domain experts manually selecting a numerical or categorical value representing the difficulty of each question, which is not scalable, intrinsically subjective and inconsistent. The other approach, pretesting, consists of deploying the new questions in an exam, as if they were standard questions, but without us","cbCaipgZM0VAE3A2","https://ap.wps.com/l/cbCaipgZM0VAE3A2","pdf",1210559,35,"English","# Introduction\n## Question Difficulty Estimation and its importance\n## Traditional approaches: manual calibration and pretesting\n## Motivation for text-based estimation (QDET)","[{\"question\":\"What is question difficulty estimation (QDE) in educational settings?\",\"answer\":\"QDE estimates a numerical or categorical value representing a question’s difficulty for educational use. It supports calibration needed for effective testing and student evaluation.\"},{\"question\":\"Why is accurate question difficulty calibration important?\",\"answer\":\"Miscalibrated questions can present inappropriate difficulty levels, harming learning outcomes and reducing the accuracy of student skill assessment. Tests that are too easy or too hard also produce uninformative score ranges.\"},{\"question\":\"How do traditional approaches like manual calibration and pretesting differ from text-based QDET?\",\"answer\":\"Manual calibration relies on experts assigning difficulty values, which is subjective and not scalable. Pretesting administers new items without scoring them, then uses responses to calibrate later, but it introduces delays and exposure risks. Text-based QDET uses question text with NLP to estimate difficulty automatically, reducing dependence on pretesting and manual labeling.\"}]","A survey on recent approaches to question difficulty estimation from text | PDF",88]