A framework for ranking and categorizing medical documents

Al Zamıl, Mohammed GH. I.
In this dissertation, we present a framework to enhance the retrieval, ranking, and categorization of text documents in medical domain. The contributions of this study are the introduction of a similarity model to retrieve and rank medical textdocuments and the introduction of rule-based categorization method based on lexical syntactic patterns features. We formulate the similarity model by combining three features to model the relationship among document and construct a document network. We aim to rank retrieved documents according to their topics; making highly relevant document on the top of the hit-list. We have applied this model on OHSUMED collection (TREC-9) in order to demonstrate the performance effectiveness in terms of topical ranking, recall, and precision metrics. In addition, we introduce ROLEX-SP (Rules Of LEXical Syntactic Patterns); a method for the automatic induction of rule-based text-classifiers relies on lexical syntactic patterns as a set of features to categorize text-documents. The proposed method is dedicated to solve the problem of multi-class classification and feature imbalance problems in domain specific text documents. Furthermore, our proposed method is able to categorize documents according to a predefined set of characteristics such as: user-specific, domain-specific, and query-based categorization which facilitates browsing documents in search-engines and increase users ability to choose among relevant documents. To demonstrate the applicability of ROLEX-SP, we have performed experiments on OHSUMED (categorization collection). The results indicate that ROLEX-SP outperforms state-of-the-art methods in categorizing short-text medical documents.


Using learning to rank for a top-n recommendation system in TV domain
Acar, Bedia; Çiçekli, Fehime Nihan; Department of Computer Engineering (2016)
In this thesis, a top-N recommendation system in TV domain is proposed using learning to rank. The design, development and evaluation of the proposed recommender system are described in detail. Instead of calculating rating score of items like in conventional recommender systems, the ranked recommendation item list is presented to TV users. Moreover, path-based features which are used to build ranking model is explained in detail. These features provide collaborative filtering, content-based filtering and c...
Factors that affect the duration of cmmi-based software process improvement initiatives
Karagül, Yasemin; Bilgen, Semih; Department of Information Systems (2009)
Reference models developed for software process improvement (SPI) provide guidelines about what to do while assessing and improving the processes, but they do not answer the questions of how. There have been a number of studies that try to find effective and strategic implementation models or to identify factors that affect the SPI success. However, these studies do not provide answers to questions about the effect of these factors on SPI program duration or accelerated SPI studies. This study aims to inves...
A method for decentralized business process modeling
Türetken, Oktay; Demirörs, Onur; Department of Information Systems (2007)
This thesis study proposes a method for organizations to perform business process modeling in a decentralized and concurrent manner. The Plural method is based on the idea that organizations’ processes can be modeled by individuals actually performing the processes. Instead of having a central and devoted group of people to understand, analyze, model and improve processes, individuals are held responsible to model and improve their own processes concurrently. These individual models are then integrated to f...
Process based information systems evaluation: Towards the attributes of "pRISE"
Özkan Yıldırım, Sevgi; Bilgen, Semih (2007-10-31)
Purpose The purpose of this paper is to demonstrate the importance of undertaking a systemic view of information systems evaluation that augments the frequently reported prescriptive (cost/benefit) analysis approaches. Design/methodology/approach The paper adopts a qualitative case perspective and derives a framework for substantive information systems evaluation factors (PRISE). Three empirical formulations are considered and a comparison made to determine the content and context of the findings. Finding...
An inspection approach for conceptual models of the mission space in a domain specific notation
Tanrıöver, Ö. Özgür; Bilgen, Semih; Department of Information Systems (2008)
An inspection approach is proposed for improving the quality of conceptual models developed in a domain specific notation. First, the process of identification of desirable properties of conceptual models in a domain specific notation is described. Intra- and interview properties are considered. Semantic properties are defined considering the conceptual modeling notation. A systematic inspection process is proposed for checking semantic properties of different types of diagrams and of the relations between ...
Citation Formats
M. G. I. Al Zamıl, “A framework for ranking and categorizing medical documents,” Ph.D. - Doctoral Program, Middle East Technical University, 2010.