Information extraction from text messages using data mining techniques

Ahmad, Sartaj; Varma, Rishabh

doi:10.26637/mjm0s01/05

Cited by 13 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nowadays, intelligent text understanding is implemented to solve various problems [2]. For example, text analysis algorithms are used to monitor social media in order to identify and prevent various events [3,4]. Basic features of the implementation of the morphological analysis of informal texts on the Internet are considered in [5].…”

Section: State-of-the-artmentioning

confidence: 99%

Hybridization of Intelligent Solutions Architecture for Text Understanding and Text Generation

et al. 2021

View full text Add to dashboard Cite

This study proposes a new logical model for intelligent software architecture devoted to improving the efficiency of automated text understanding and text generation in industrial applications. The presented approach introduces a few patterns that provide a possibility to build adaptable and extensible solutions using machine learning technologies. The main idea is formalized by the concept of expounder hybridization. It summarizes an experience of document analysis and generation solutions development and social media analysis based on artificial neural networks’ practical use. The results of solving the task by the best expounder were improved using the method of aggregating multiple expounders. The quality of expounders’ combination can be further improved by introducing the pro-active competition between them on the basis of, e.g., auctioning algorithm, using several parameters including precision, solution performance and score. Analysis of the proposed approach was carried out using a dataset of legal documents including joint-stock company decision record sheets and protocols. The solution is implemented in an enterprise content management system and illustrated by an example of processing of legal documentation.

show abstract

Section: State-of-the-artmentioning

confidence: 99%

Hybridization of Intelligent Solutions Architecture for Text Understanding and Text Generation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Several techniques have been used to analyze Arabic texts (Ahmad and Varma, 2018; Adeleke et al , 2017; Saleem and Martha, 2004) and introduced a method that merges shallow parsing and data mining (DM) techniques with traditional data retrieval. AL-Kabi et al (2005) created an automatic classifier to categorize the verses of “ Fatiha” and El-Halees (2007) designed a system called ArabCat based on maximum entropy model to categorize Arabic documents.…”

Section: Literature Reviewsmentioning

confidence: 99%

Screening of Murabaha business process through Quran and hadith: a text mining analysis

Tlemsani

Marir

Majdalawieh

2020

JIABR

View full text Add to dashboard Cite

Purpose This paper revolves around the usage of data analytics in the Qur’an and Hadith through a new text mining technique to answer the main research question of whether the activities and the data flows of the Murabaha financing contract is compatible with Sharia law. The purpose of this paper is to provide a thorough and comprehensive database that will be used to examine existing practices in Islamic banks’ and improve compliancy with Islamic financial law (Sharia). Design/methodology/approach To design a Sharia-compliant Murabaha business process originated on text mining, the authors start by identifying the factors deemed necessary in their text mining techniques of both texts; using a four-step strategy to analyze those text mining analytics; then, they list the three basic approaches in text mining used for new knowledge discovery in databases: the co-occurrence approach based on the recursive co-occurrence algorithm; the machine learning or statistical-based; and the knowledge-based. They identify any variation and association between the Murabaha business processes produced using text mining against the one developed through data collection. Findings The main finding attained in this paper is to confirm the compatibility of all activities and the data flows in the Murabaha financing contract produced using data analytics of the Quran and Hadith texts against the Murabaha business process that was developed based on data collection. Another key finding is revealing some shortcomings regarding Islamic banks business process compliance with Sharia law. Practical implications Given Murabaha as the most popular mode of Islamic financing with more than 75% in total transactions, this research has managed to touch-base on an area that is interesting to the vast majority of those dealing with Islamic finance instruments. By reaching findings that could improve the existing Islamic Murabaha business process and concluding on Sharia compliance of the existing Murabaha business process, this research is quite relevant and could be used in practice as well as in influencing public policy. In fact, Islamic Sharia law experts, Islamic finance professionals and Islamic banks may find the results of this study very useful in improving at least one aspect of the Islamic finance transactions. Originality/value By using a novel, fresh text mining methods built on recursive occurrence of synonym words from the Qur’an and Hadith to enrich Islamic finance, this research study can claim to have been the first of its kind in using machine learning to mine the Quran, Hadith and in extracting valuable knowledge to support and consolidate the Islamic financial business processes and make them more compliant with the i.

show abstract

“…Text mining atau text data mining, adalah bidang pengetahuan yang mencakup area information retrieval [8], text analysis, information extraction [9], clustering [10], categorization [3] [5], visualization, database technology, machine learning, dan data mining [11].…”

Section: A Text Miningunclassified

Implementasi Algoritma K-Nearest Neighbor untuk Melakukan Klasifikasi Produk dari beberapa E-marketplace

Sebastián¹

2019

JuTISI

View full text Add to dashboard Cite

E-marketplace has gained popularity with the Indonesian society resulting in the increment of products offered. Consequently, customers require more effort to search for products. In this study, we classified products from several e-marketplaces. The classification was carried out using TF-IDF method for the weighting, cosine similarity to calculate product similarity distance, and k-nearest neighbor algorithm. Based on the first testing result using 150 product data, the k-nearest neighbor method with k=5 successfully classified 146 data with 4 data classified into the wrong class. This k=5 value gives the best result for this case, with an accuracy of 97.33%. The second testing result using 150 mixed brand product data, the k-nearest neighbor method successfully classified 145 data with 5 data classified into the wrong class. The accuracy of the second testing is 96.67%.

show abstract

Information extraction from text messages using data mining techniques

Cited by 13 publications

References 16 publications

Hybridization of Intelligent Solutions Architecture for Text Understanding and Text Generation

Hybridization of Intelligent Solutions Architecture for Text Understanding and Text Generation

Screening of Murabaha business process through Quran and hadith: a text mining analysis

Implementasi Algoritma K-Nearest Neighbor untuk Melakukan Klasifikasi Produk dari beberapa E-marketplace

Contact Info

Product

Resources

About