Scholarlink

In today’s dossier-steered world, competently retrieving applicable particulars has enhanced as a challenging platform, specifically in the field of academic data retrieval. With the moderations in the AI models, machine learning tools, and motorized data analysis it’s quite feasible to develop query analysis by categorizing boundaries, analyzing complexity, and ascertaining the weightage of queries. This paper instigates Semantic Model for Retrieval and Interpretation of Topical Information (SMRITI), a novel Semantic Web-based structure specifically customized for the academic institutional domain. SMRITI utilizes frameworks’ portrayal of knowledge, corresponding to various layers of semantic architecture to encourage efficient examination question retrieval and comprehensive analytics. By leveraging semantic mechanisms, it provides intelligent explorations based on relationships, concepts, and context, enhancing the significance of retrieved questions. Furthermore, the model embodies data retrieval techniques like web scraping (using BeautifulSoup, Selenium, and Requests HTML) and Keyword extraction methods (using TF-IDF, TextRank, KeyBERT, RAKE-NLTK, YAKE, and SPACY) to interpret and scrutinize topical information effectively. Additionally, SMRITI incorporates educators with powerful analytical methods to appraise question difficulty, monitor student’s performance, and identify knowledge gaps. This proposal assures the revolutionization of smart E-learning by promoting personalized learning experiences and assisting data-driven instructional decisions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SMRITI—Semantic Model for Retrieval and Interpretation of Topical Information

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Debayan De,
  • Kartik Tulsian,
  • Rupayan Das,
  • Subhabrata Sengupta,
  • Avijit Bose,
  • Kajari Sur

摘要

In today’s dossier-steered world, competently retrieving applicable particulars has enhanced as a challenging platform, specifically in the field of academic data retrieval. With the moderations in the AI models, machine learning tools, and motorized data analysis it’s quite feasible to develop query analysis by categorizing boundaries, analyzing complexity, and ascertaining the weightage of queries. This paper instigates Semantic Model for Retrieval and Interpretation of Topical Information (SMRITI), a novel Semantic Web-based structure specifically customized for the academic institutional domain. SMRITI utilizes frameworks’ portrayal of knowledge, corresponding to various layers of semantic architecture to encourage efficient examination question retrieval and comprehensive analytics. By leveraging semantic mechanisms, it provides intelligent explorations based on relationships, concepts, and context, enhancing the significance of retrieved questions. Furthermore, the model embodies data retrieval techniques like web scraping (using BeautifulSoup, Selenium, and Requests HTML) and Keyword extraction methods (using TF-IDF, TextRank, KeyBERT, RAKE-NLTK, YAKE, and SPACY) to interpret and scrutinize topical information effectively. Additionally, SMRITI incorporates educators with powerful analytical methods to appraise question difficulty, monitor student’s performance, and identify knowledge gaps. This proposal assures the revolutionization of smart E-learning by promoting personalized learning experiences and assisting data-driven instructional decisions.