Ranking of text documents using TF-IDF weighting and association rules mining

Jabri, Siham; Dahbi, Azzeddine; Gadi, Taoufiq; Bassir, Abdelhak

doi:10.1109/icoa.2018.8370597

Cited by 29 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Name": "8.1", "contents": [ "8.1", "Seller's Insurance", "During this term unless otherwise self insured Seller will maintain the", "following insurance coverage", "(a)", "During ",…..], "sections": "" }, { "Name": "8.3", "contents": [ "8.3", "Failure To Maintain Insurance", "Failure of any Party to maintain the insurance required under this Section 8 shall",………], "sections": "" }, { "Name": "8. that N <=3). Then, TF-IDF [10,12] is computed for the tokens. Each section/subsection of the documents is transformed into a vector space, where the entries of vector are TF-IDF values.…”

Section: Document Reconstructionmentioning

confidence: 99%

Automatic knowledge extraction from OCR documents using hierarchical document analysis

Masum

Kosaraju

Bayramoglu³

et al. 2018

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems

View full text Add to dashboard Cite

Industries can improve their business efficiency by analyzing and extracting relevant knowledge from large numbers of documents. Knowledge extraction manually from large volume of documents is labor intensive, unscalable and challenging. Consequently, there have been a number of attempts to develop intelligent systems to automatically extract relevant knowledge from OCR documents. Moreover, the automatic system can improve the capability of search engine by providing application-specific domain knowledge. However, extracting the efficient information from OCR documents is challenging due to highly unstructured format [1, 11, 18, 26]. In this paper, we propose an efficient framework for a knowledge extraction system that takes keywords based queries and automatically extracts their most relevant knowledge from OCR documents by using text mining techniques. The framework can provide relevance ranking of knowledge to a given query. We tested the proposed framework on corpus of documents at GE Power where document consists of more than hundred pages in PDF.

show abstract

Section: Document Reconstructionmentioning

confidence: 99%

Automatic knowledge extraction from OCR documents using hierarchical document analysis

Masum

Kosaraju

Bayramoglu³

et al. 2018

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems

View full text Add to dashboard Cite

show abstract

“…It helps connect people with common interests [3] and provides new opportunities to improve public health and medicine; the prediction of post-liver transplantation survival is one example [4,5]. This technique helps users find documents relevant to their search [8] and potentially leads to beneficial services. However, privacy remains a critical issue [15].…”

Section: Related Workmentioning

confidence: 99%

“…The crossover is done by generating one random vector with the same length as the parents; for example, R = (1, 0, 1, 0). Then the child will inherit its genes from A in the case of 1 and from B in the case of 0: Child = (1, 8,6,9). Following the crossover, mutation is performed, which provides a minor tweak to a chromosome to obtain diverse solutions.…”

Section: Tracing Examplementioning

confidence: 99%

“…In a set of transactions, ARM focuses on finding associations between frequent items, enabling researchers to predict the frequency of one itemset depending on the frequency of another item in a transaction. The ARM technique has been extensively used in several applications, including privacy preservation [1], market-basket transaction data analysis [2], recommendation [3], health care [4,5], prediction [6], pattern finding in web browsing [7], ranking of text documents [8], and hazard identification [9], among others. The extraction of association rules from transaction datasets was initiated in 1993 [10].…”

Section: Introductionmentioning

confidence: 99%

“…Another technique, privacy preservation data mining (PPDM), has also gained considerable attention in transactional datasets [8]. PPDM maintains privacy by allowing the discovery of nonsensitive information and protecting sensitive information from disclosure.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient Association Rules Hiding Using Genetic Algorithms

Bux

Wang

et al. 2018

Symmetry

View full text Add to dashboard Cite

In today’s world, millions of transactions are connected to online businesses, and the main challenging task is ensuring the privacy of sensitive information. Sensitive association rules hiding (SARH) is an important goal of privacy protection algorithms. Various approaches and algorithms have been developed for sensitive association rules hiding, differentiated according to their hiding performance through utility preservation, prevention of ghost rules, and computational complexity. A meta-heuristic algorithm is a good candidate to solve the problem of SARH due to its selective and parallel search behavior, avoiding local minima capability. This paper proposes simple genetic encoding for SARH. The proposed algorithm formulates an objective function that estimates the effect on nonsensitive rules and offers recursive computation to reduce them. Three benchmark datasets were used for evaluation. The results show an improvement of 81% in execution time, 23% in utility, and 5% in accuracy.

show abstract