[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-501647-105":59,"doc-detail-501647-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","from-app-features-to-explanation-needs-analyzing-correlations-and-predictive-potential","From App Features to Explanation Needs - Analyzing Correlations and Predictive Potential","","Software systems need to help users understand not only how to use an app, but also why certain behaviors occur. This study tests whether explanation needs—derived from user reviews—can be predicted from app properties. Using 4,495 reviews enriched with metadata such as app version, ratings, age restriction, and in-app purchases, correlation and regression analyses show mostly weak associations and limited predictive power. Validation on 495 manually labeled reviews confirms that explanation needs are highly context-dependent, especially for interaction and UI.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/from-app-features-to-explanation-needs-analyzing-correlations-and-predictive-potential/501647/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/from-app-features-to-explanation-needs-analyzing-correlations-and-predictive-potential/501647.png","ImageObject",300,407,{"name":92,"@type":93},"Pentious","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-16","2026-10-03",true,{"@type":102,"interactionType":103,"userInteractionCount":81},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of this study?","Question",{"text":112,"@type":113},"To determine whether explanation needs extracted from app reviews can be correlated with, or predicted from, readily available app properties and metadata.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which data sources and metadata are used?",{"text":117,"@type":113},"The study analyzes a gold standard dataset of 4,495 app reviews enriched with metadata including app version, ratings, age restriction, and in-app purchases, and it validates with 495 expert-labeled reviews.",{"name":119,"@type":110,"acceptedAnswer":120},"How strong are the relationships between app properties and explanation needs?",{"text":121,"@type":113},"Correlation analyses show mostly weak associations, with moderate correlations only for certain features like app version, number of reviews, and star ratings; linear regression provides limited predictive power without reliable forecasts.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},501647,1792165584,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":81,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":46},1374404730887,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","From App Features to Explanation Needs: Analyzing Correlations and Predictive Potential  \nMartin Obaidi, Kushtrim Qengaj, Jakob Droste, Hannah Deters, Marc Herrmann, Elisa Schmid, Kurt Schneider  \nLeibniz Universitt Hannover, Software Engineering Group Hannover, Germany  \n{martin.obaidi, jakob.droste, hannah.deters}@inf.uni-hannover.de,{marc.herrmann, elisa.schmid, kurt.schneider}@inf.uni-hannover.de, [kushtrim.qengaj@stud.uni-hannover.de](kushtrim.qengaj@stud.uni-hannover.de)  \nJil Kl¨under  \nUniversity of Applied Sciences FHDW Hannover Hannover, Germany jil.kluender@fhdw.de  \narXiv :2508 .03881v2 [ cs . SE] 20 Aug 2025  \nAbstract—In today’s digitized world, software systems must support users in understanding both how to interact with a system and why certain behaviors occur. This study investigates whether explanation needs, classified from user reviews, can be predicted based on app properties, enabling early consideration during development and large-scale requirements mining. We analyzed a gold standard dataset of 4,495 app reviews enriched with metadata (e.g., app version, ratings, age restriction, inapp purchases). Correlation analyses identified mostly weak associations between app properties and explanation needs, with moderate correlations only for specific features such as app version, number of reviews, and star ratings. Linear regression models showed limited predictive power, with no reliable forecasts across configurations. Validation on a manually labeled dataset of 495 reviews confirmed these findings. Categories such as Security & Privacy and System Behavior showed slightly higher predictive potential, while Interaction and User Interface remained most difficult to predict. Overall, our results highlight that explanation needs are highly context-dependent and cannot be precisely inferred from app metadata alone. Developers and requirements engineers should therefore supplement metadata analysis with direct user feedback to effectively design explainable and usercentered software systems.  \nIndex Terms—explainability, requirements engineering, data mining, app reviews  \nI. INTRODUCTION  \nModern software systems are becoming ever more complex and opaque, making it difficult for users to understand and trust system behavior—especially in AI-driven or data-rich domains [1], [2],[3] . As a result, explainability has emerged asa crucial non-functional requirement, supporting transparency, trust, and regulatory needs [4], [5], [6], [7], [8] . Explanations enhance not just comprehension but also usability, safety, and satisfaction, notably in sensitive areas like healthcare or privacy [9], [10], [11] .  \nDespite its importance, explainability remains challenging to operationalize in requirements engineering (RE) [12], [13] . User needs for explanations are often expressed informally, through app reviews [14], support requests, or other feedback channels [15], [16], [17], making systematic identification and structuring difficult [18], [19] . Needs also vary by context, task, expertise, and even mood [20], [21], [22], further complicating requirements elicitation and targeted design.  \nCrowd-based Requirements Engineering (CrowdRE) leverages user-generated content such as app reviews as a rich source for uncovering implicit explanation needs [23], [24],[18] . Taxonomies help structure and automate the identification of these needs, for example by classifying explicit/implicit requests or mapping needs to system aspects like User Interface, Security, or Interaction [23], [18], [19] .  \nA key open question remains: To what extent can explanation needs be predicted from readily available app properties or metadata (e.g., app category, star ratings) rather than costly user studies or manual review analysis? [25], [10] . If such properties offer predictive value, developers and UX designers could proactively identify and address explanation needs, informing onboarding, help documentation, or targeted feature improvements ","cbCain4onpTify61","https://ap.wps.com/l/cbCain4onpTify61","pdf",325500,"English","# Introduction\n## Background and Related Work\n### Explainability as a Software Quality Aspect\n## Study Design and Method\n## Results and Evaluation\n## Discussion and Conclusion","[{\"question\":\"What is the main goal of this study?\",\"answer\":\"To determine whether explanation needs extracted from app reviews can be correlated with, or predicted from, readily available app properties and metadata.\"},{\"question\":\"Which data sources and metadata are used?\",\"answer\":\"The study analyzes a gold standard dataset of 4,495 app reviews enriched with metadata including app version, ratings, age restriction, and in-app purchases, and it validates with 495 expert-labeled reviews.\"},{\"question\":\"How strong are the relationships between app properties and explanation needs?\",\"answer\":\"Correlation analyses show mostly weak associations, with moderate correlations only for certain features like app version, number of reviews, and star ratings; linear regression provides limited predictive power without reliable forecasts.\"}]","From App Features to Explanation Needs - Analyzing Correlations and Predictive Potential | PDF",1791022036]