{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:09:39Z","timestamp":1781626179763,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Evaluating descriptive answers is complex and challenging due to the multiple answers provided by students. Although there are approaches for solving the problem of descriptive answer grading, the focus of such methods is on short answers rather than long answers. This work proposes a new model based on estimating similarity scores between question-answers and schema and answers. The proposed work asserts that the schema provides the right words and sentences, considered references for grading descriptive answers. Similarly, the question words also provide vital information about the right answers. We explore the SentenceTransformer model and cosine distance measure to estimate the similarity score, which results in feature vectors. The SentenceTransformer is proposed for estimating semantic similarity between two sentences, while cosine similarity is proposed for estimating the degree of similarity between two words. Inspired by the success of the 1D convolutional neural network in classification, we adopted the 1D-CNN with fully connected dense layers for grading answers by feeding the feature vectors. This CNN model classifies descriptive answers into three categories: A (right answer), B (partially correct answer), and C (wrong answer). To demonstrate the significance of the proposed method, we conducted experiments on our dataset and compared its performance with state-of-the-art methods. The results show that the proposed model outperforms the existing methods in terms of the confusion matrix and average classification rate.<\/jats:p>","DOI":"10.1007\/s42979-025-04628-4","type":"journal-article","created":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T11:00:19Z","timestamp":1766746819000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Estimating Similarity for Grading Descriptive Handwritten Answers"],"prefix":"10.1007","volume":"7","author":[{"given":"Garvit","family":"Ahuja","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9026-4613","authenticated-orcid":false,"given":"Shivakumara","family":"Palaiahnakote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nilanjana","family":"Chatterjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mo","family":"Saraee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,26]]},"reference":[{"key":"4628_CR1","volume-title":"Revolutionizing subjective assessment: A three-pronged comprehensive approach with NLP and deep learning","author":"R Agrawal","year":"2024","unstructured":"Agrawal R, Mishra H, Kandasamy I, Terni SR, Vasantha WB. Revolutionizing subjective assessment: A three-pronged comprehensive approach with NLP and deep learning. Expert Systems with Applications; 2024."},{"key":"4628_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed J, Hina S, Asif R. Evaluation of descriptive answers of open-ended questions using NLP techniques, In Proc. ICCIS, 2021.","DOI":"10.1109\/ICCIS54243.2021.9676405"},{"key":"4628_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19999-8","author":"G Ahuja","year":"2024","unstructured":"Ahuja G, Alaei A, Pal U. A new multimodal sentiment analysis for images containing textual information. Multimedia Tools Appl. 2024;84:23745\u201374. https:\/\/doi.org\/10.1007\/s11042-024-19999-8.","journal-title":"Multimedia Tools Appl"},{"key":"4628_CR4","doi-asserted-by":"crossref","unstructured":"Bagaria V, Badve M, Beldar M, Ghane S. An intelligent system for evaluation of descriptive answers, In Proc. ICISSS, pp 19\u201324, 2020.","DOI":"10.1109\/ICISS49785.2020.9316110"},{"key":"4628_CR5","doi-asserted-by":"crossref","unstructured":"Bansode G, Jha DK, Hasabnis A, Nayak A, Pagare R. A transfer learning approach for descriptive question answering system, In Proc. PuneConf. pp 1\u20137, 2021.","DOI":"10.1109\/PuneCon52575.2021.9686521"},{"key":"4628_CR6","doi-asserted-by":"crossref","unstructured":"Bashir MF, Arshad H, Javed AR, Band SS. Subjective answer evaluation using machine learning and natural language processing, IEEE Access, pp 158972\u2013158983, 2021.","DOI":"10.1109\/ACCESS.2021.3130902"},{"key":"4628_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117315","author":"N Birla","year":"2022","unstructured":"Birla N, Jain MK, Panwar A. Automated assessment of subjective assignments: a hybrid approach. Expert Syst Appl. 2022. https:\/\/doi.org\/10.1016\/j.eswa.2022.117315.","journal-title":"Expert Syst Appl"},{"key":"4628_CR8","doi-asserted-by":"crossref","unstructured":"Chatterjee NC, Shivakumara P, Pal U, Lu T, Lu Y. Anomaly handwritten text detection for automatic descriptive answer evaluation, In Proc. ICCPR, pp 334\u2013340, 2022.","DOI":"10.1145\/3581807.3581855"},{"key":"4628_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116108","author":"NB Chaudhuri","year":"2022","unstructured":"Chaudhuri NB, Dhar D, Yammiyavar PG. Automating assessment of design exams: a case study of novelty evaluation. Expert Syst Appl. 2022. https:\/\/doi.org\/10.1016\/j.eswa.2021.116108.","journal-title":"Expert Syst Appl"},{"key":"4628_CR10","unstructured":"Condor A, Litster M, Pardos Z. Automatic short answer grading with SBERT on Out-of-Sample questions. Int Educational Data Min Soc (2021)."},{"key":"4628_CR11","doi-asserted-by":"crossref","unstructured":"Das A, Suwanwiwat H, Pal U, Blumenstein M. ICFHR 2020 competition on short answer assessment and Thai student signature and names components recognition and verification, In Proc. ICFHR, pp 222\u2013227, 2020.","DOI":"10.1109\/ICFHR2020.2020.00049"},{"issue":"18","key":"4628_CR12","doi-asserted-by":"publisher","first-page":"53441","DOI":"10.1007\/s11042-023-17606-w","volume":"83","author":"A Das","year":"2024","unstructured":"Das A, Suwanwiwat H, Pal U. A novel multi-task learning technique for offline handwritten short answer spotting and recognition. Multimed Tools Appl. 2024;83(18):53441\u201365.","journal-title":"Multimed Tools Appl"},{"key":"4628_CR13","doi-asserted-by":"crossref","unstructured":"Dodia S, Spoorthy V, Chandak T. Machine learning-based automated system for subjective answer evaluation, In Proc. CONECCT, 2023.","DOI":"10.1109\/CONECCT57959.2023.10234818"},{"key":"4628_CR14","unstructured":"Google Cloud. (n.d.). OCR with Vision AI: Extract text from images using Optical Character Recognition. Google Cloud. Retrieved January 28. 2025, from https:\/\/cloud.google.com\/vision"},{"key":"4628_CR15","doi-asserted-by":"crossref","unstructured":"Hussain MG, Kabir S, Mahmud TA, Khatun A, Islam MJ. Assessment of Bangla descriptive answer script digitally, In Proc. ICVSLP, 2019.","DOI":"10.1109\/ICBSLP47725.2019.202042"},{"key":"4628_CR16","doi-asserted-by":"crossref","unstructured":"Kapoor BSJ, Nagpure SM, Kolhatkar SS, Ghanaor PG, Vishwakarma MM, Kokate RB. An analysis of automated answer evaluation systems based on machine learning, In Proc. ICICT, pp 439\u2013443, 2020.","DOI":"10.1109\/ICICT48043.2020.9112429"},{"key":"4628_CR17","doi-asserted-by":"crossref","unstructured":"Kumar AP, Nayak A, Shenoy MK, Goyal S. A novel approach to generate distractors for multiple choice questions. Experts Syst Appl, 2023.","DOI":"10.1016\/j.eswa.2023.120022"},{"key":"4628_CR18","doi-asserted-by":"crossref","unstructured":"Oasis AS, Ebenezer AM, Sharma D, Sada R, Arya A. Question-centric evaluation of descriptive answers using attention-based architecture, In Proc. ICCCDSE, pp 20\u201325, 2022.","DOI":"10.1109\/Confluence52989.2022.9734117"},{"key":"4628_CR19","doi-asserted-by":"crossref","unstructured":"Raghunandan KS, Shivakumara P, Navya BJ, Pooja G, Prakash N, Kumar GH, Pal U, Lu T. Fourier coefficients for fraud handwritten document classification through age analysis, In Proc. ICFHR, pp 26\u201330, 2016.","DOI":"10.1109\/ICFHR.2016.0018"},{"key":"4628_CR20","doi-asserted-by":"publisher","DOI":"10.14738\/tmlai.104.12831","author":"M Rahaman","year":"2022","unstructured":"Rahaman M, Mahmud H. Automated Evaluation of Handwritten Answer Script Using Deep Learning Approach. Trans Mach Learn Artif Intell. 2022. https:\/\/doi.org\/10.14738\/tmlai.104.12831.","journal-title":"Trans Mach Learn Artif Intell"},{"key":"4628_CR21","doi-asserted-by":"crossref","unstructured":"Reimers N. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv preprint arXiv:1908.10084 (2019).","DOI":"10.18653\/v1\/D19-1410"},{"issue":"27","key":"4628_CR22","doi-asserted-by":"publisher","first-page":"41913","DOI":"10.1007\/s11042-023-15191-6","volume":"82","author":"LS Riza","year":"2023","unstructured":"Riza LS, Firdaus Y, Sukamto RA, Wahyudin, Abu Samah KAF. Automatic generation of short-answer questions in reading comprehension using NLP and KNN. Multimedia Tools Appl. 2023;82(27):41913\u201340.","journal-title":"Multimedia Tools Appl"},{"key":"4628_CR23","doi-asserted-by":"crossref","unstructured":"Rowtula V, Oota SR, Jawahar CV. Towards automated evaluation of handwritten assessments, In Proc. ICDAR, pp 426\u2013433, 2019.","DOI":"10.1109\/ICDAR.2019.00075"},{"key":"4628_CR24","doi-asserted-by":"crossref","unstructured":"Sanuvala G, Fatima SS. A study of automated evaluation of student\u2019s examination paper using machine learning techniques, In Proc. ICCCIS, pp 1049\u20131054, 2021.","DOI":"10.1109\/ICCCIS51004.2021.9397227"},{"key":"4628_CR25","doi-asserted-by":"crossref","unstructured":"Sayeed MA, Gupta D. Automate descriptive answer grading using reference based models, In Proc. OCIT, pp 262\u2013267, 2022.","DOI":"10.1109\/OCIT56763.2022.00057"},{"key":"4628_CR26","doi-asserted-by":"publisher","first-page":"35253","DOI":"10.1007\/s11042-023-14558-z","volume":"82","author":"A Sharma","year":"2023","unstructured":"Sharma A, Katlaa R, Kaur G, et al. Full-page handwriting recognition and automated essay scoring for in-the-wild essays. Multimed Tools Appl. 2023;82:35253\u201376.","journal-title":"Multimed Tools Appl"},{"key":"4628_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118266","author":"P Shivakumara","year":"2022","unstructured":"Shivakumara P, Jain T, Pal U, Surana N, Antonacopoulos A, Lu T. Text line segmentation from struck-out handwritten document images. Expert Syst Appl. 2022. https:\/\/doi.org\/10.1016\/j.eswa.2022.118266.","journal-title":"Expert Syst Appl"},{"key":"4628_CR28","doi-asserted-by":"crossref","unstructured":"Shylesh A, Mathin S, Shanmugasundaram H. Automated answer script evaluation using deep learning, In Proc. ICCCI, 2023.","DOI":"10.1109\/ICCCI56745.2023.10128311"},{"key":"4628_CR29","doi-asserted-by":"crossref","unstructured":"Sreevidhya V, Narayanam J. Short descriptive answers evaluation using word-embedding techniques, In Proc. ICCCNT, 2021.","DOI":"10.1109\/ICCCNT51525.2021.9579636"},{"key":"4628_CR30","doi-asserted-by":"crossref","unstructured":"Thalor MA. A descriptive answer evaluation system using cosine similarity technique, In Proc. ICCICT, 2021.","DOI":"10.1109\/ICCICT50803.2021.9510170"},{"issue":"5","key":"4628_CR31","doi-asserted-by":"publisher","first-page":"6131","DOI":"10.1007\/s11042-021-11771-6","volume":"81","author":"D Viji","year":"2022","unstructured":"Viji D, Revathy S. A hybrid approach of weighted fine-tuned BERT extraction with deep Siamese Bi\u2013LSTM model for semantic text similarity identification. Multimed Tools Appl. 2022;81(5):6131\u201357.","journal-title":"Multimed Tools Appl"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04628-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04628-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04628-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:48:52Z","timestamp":1781624932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04628-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,26]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["4628"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04628-4","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,26]]},"assertion":[{"value":"18 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Funding and\/or Conflicts of interest\/Competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not Applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Ethical Approval"}},{"value":"Not Applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent To Participate"}},{"value":"The authors have no objection to publishing the work after acceptance.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent To Publish"}}],"article-number":"46"}}