بررسی دعاهای صحیفه سجادیه از منظر روش های متن کاوی

نوع مقاله : علمی- پژوهشی

نویسندگان

• محمد فیاض ¹
• نزهت شاکری ²

¹ دکترای تخصصی آمارزیستی ، استادیار ( استاد مدعو)، دانشکده بیمه اکو، دانشگاه علامه طباطبائی، تهران، ایران

² گروه آمارزیستی، دانشکده پیراپزشکی، دانشگاه علوم پزشکی شهیدبهشتی، تهران، ایران

چکیده

کلیدواژه‌ها

• صحیفه سجادیه
• متن کاوی
• ابرکلمات
• نرم افزار R
• خوشه بندی
• شبکه ی متنی
• بیمه

Studying the al-Sahifa al-Sajjadiyya Supplications with the Text Mining Methods

 Nezhat Shakeri[1] , Mohammad Fayaz[2] *

Abstract

Many studies using text mining methods to investigate hidden patterns, frequent words, comparison purposes, checking the originality of the text of famous books in religious sciences such as the Holy Quran, the Holy Bible or classical literature such as the works of Persian poets, the works of William Shakespeare, Johann Wolfgang von Goethe and ... have been done. In the meantime, the al-Sahifa al-Sajjadiyya Supplications attributed to Imam Ali ibn Husayn Zayn al-Abidin (AS) is one of the most well-known sources of studies in Shiite sciences about prayer. But so far, the text mining study has not been done in this text and this work examines a descriptive method called world cloud in these prayers. This is the first step for further research in this field. First, all 54 prayers of this text were extracted from books and the internet, and then they were prepared for analysis. The words of each prayer have been separated with R and their descriptive statistics, text and word networks, word clouds and clustering based on them are conducted. A total of 15,881 words were recognized. The words "Allahomma", "Muhammad", "Allah", "Sal" and "Kol" had the highest frequency of 285, 239, 208 and 144 respectively, and together with other words, the word cloud is shown. Also, word cloud for each prayer are drawn in the appendix separately. The descriptive statistics, clustering and text networks are estimated. This research examines the patterns of repetition of words in each prayer. It also presents some related examples with the insurance subjects. The limitations and future directions of this work in developing the text mining and data analysis methods are pointed out.

Keywords: al-Sahifa al-Sajjadiyya, Text Mining, Word Cloud, R Language

[1]-Department of Biostatistics, School of Allied Medical Sciences, Shahid Beheshti University of Medical sciences, Tehran, nezhat2000@yahoo.com

[2]-PhD in Biostatistics, Assistant Professor (Visiting Professor), ECO College of Insurance, Allameh Tabataba'i University, Mohammad.Fayaz.89@gmail.com