Browsing by Author "Kilinç, D"

Now showing 1 - 11 of 11
  • No Thumbnail Available
    Item
    Automatic concept identification of software requirements in Turkish
    Bozyigit, F; Aktas, Ö; Kilinç, D
    Software requirements include description of the features for the target system and express the expectations of users. In the analysis phase, requirements are transformed into easy-to-understand conceptual models that facilitate communication between stakeholders. Although creating conceptual models using requirements is mostly implemented manually by analysts, the number of models that automate this process has increased recently. Most of the models and tools are developed to analyze requirements in English, and there is no study for agglutinative languages such as Turkish or Finnish. In this study, we propose an automatic concept identification model that transforms Turkish requirements into Unified Modeling Language class diagrams to ease the work of individuals on the software team and reduce the cost of software projects. The proposed work is based on natural language processing techniques and a new rule-set containing twenty-six rules is created to find object-oriented design elements from requirements. Since there is no publicly available dataset on the online repositories, we have created a well-defined dataset containing twenty software requirements in Turkish and have made it publicly available on GitHub to be used by other researchers. We also propose a novel evaluation model based on an analytical hierarchy process that considers the experts' views and calculate the performance of the overall system as 89%. We can state that this result is promising for future works in this domain.
  • No Thumbnail Available
    Item
    Twitter Fake Account Detection
    Ersahin, B; Aktas, Ö; Kilinç, D; Akyol, C
    Social networking sites such as Twitter and Facebook attracts millions of users across the world and their interaction with social networking has affected their life. This popularity in social networking has led to different problems including the possibility of exposing incorrect information to their users through fake accounts which results to the spread of malicious content. This situation can result to a huge damage in the real world to the society. In our study, we present a classification method for detecting the fake accounts on Twitter. We have preprocessed our dataset using a supervised discretization technique named Entropy Minimization Discretization (EMD) on numerical features and analyzed the results of the Naive Bayes algorithm.
  • No Thumbnail Available
    Item
    Collaborative Filtering based Course Recommender using OWA operators
    Bozyigit, A; Bozyigit, F; Kilinç, D; Nasiboglu, E
    Recommendation systems guide users to choose the most appropriate items among numerous alternatives based on predicting their interests. Recently, it is seen that recommendation systems have become to be widely used in educational domain, especially in course recommender applications. The objectives of these systems is facilitating course selection process of students and reducing their stresses. The current course recommendation studies generally consider the most recent grades of the courses taken by students and ignore the case of repeating the course under the pass-fail or grade replacement options. However, retaking a course is the primary parameter giving opinion about tendency of the students to the courses. In this study, we propose a novel collaborative filtering (CF) based course recommendation system considering the case of repeating a course and students' grades in the course for each repetition. We experiment different Ordered Weighted Averaging (OWA) operators which aggregates grades for each student's repeated courses to enhance the recommendation quality. The normalized mean absolute error (MAE) of our approach using CF and OWA is calculated as 0,063 which is encouraging for future work.
  • No Thumbnail Available
    Item
    A hybrid sentiment analysis method for Turkish
    Ersahin, B; Aktas, Ö; Kilinç, D; Ersahin, M
    This paper presents a hybrid methodology for Turkish sentiment analysis, which combines the lexicon-based and machine learning (ML)-based approaches. On the lexicon-based side, we use a sentiment dictionary that is extended with a synonyms lexicon. Besides this, we tackle the classification problem with three supervised classifiers, naive Bayes, support vector machines, and J48, on the ML side. Our hybrid methodology combines these two approaches by generating a new lexicon-based value according to our feature generation algorithm and feeds it as one of the features to machine learning classifiers. Despite the linguistic challenges caused by the morphological structure of Turkish, the experimental results show that it improves the accuracy by 7% on average.
  • No Thumbnail Available
    Item
    Multi-level reranking approach for bug localization
    Kilinç, D; Yücalar, F; Borandag, E; Aslan, E
    Bug fixing has a key role in software quality evaluation. Bug fixing starts with the bug localization step, in which developers use textual bug information to find location of source codes which have the bug. Bug localization is a tedious and time consuming process. Information retrieval requires understanding the programme's goal, coding structure, programming logic and the relevant attributes of bug. Information retrieval (IR) based bug localization is a retrieval task, where bug reports and source files represent the queries and documents, respectively. In this paper, we propose BugCatcher, a newly developed bug localization method based on multi-level re-ranking IR technique. We evaluate BugCatcher on three open source projects with approximately 3400 bugs. Our experiments show that multi-level reranking approach to bug localization is promising. Retrieval performance and accuracy of BugCatcher are better than current bug localization tools, and BugCatcher has the best Top N, Mean Average Precision (MAP) and Mean Reciprocal Rank (MRR) values for all datasets.
  • No Thumbnail Available
    Item
    Comparison of Mobile Interaction Management Products Using Systematic Literature Review Method and a New Product Suggestion
    Öztürk, S; Elmas, C; Bozyigit, F; Kilinç, D
    Because of innovations and improvements in technology, the use of smartphones that make it easier for users to work has become widespread. At this point, companies can reach their customers more easily and can communicate continuously. Once mobile applications are created, the system infrastructure needs to be improved in response to changing needs and demands to actively retain registered users and continually capture their insights. In this case, a dynamic framework that will create user profiles in a mobile application and provide services according to different user needs. In this study, the main features of the mobile interaction management applications on the market and other features they provide to create a loyal user base have been evaluated using the Systematic Literature Review (SLI) method and the necessary gaps have been discussed. In order to acquire loyal mobile-app user, Machine Learning support system is proposed as solution.
  • No Thumbnail Available
    Item
    A New Approach for Prediction of Solar Radiation with Using Ensemble Learning Algorithm
    Basaran, K; Özçift, A; Kilinç, D
    This article investigates the competence of ensemble learning techniques in solar irradiance prediction. It was seen from the literature survey, an ensemble tree model, random forests is studied more frequently as ensemble models. However, ensemble of support vector regression (SVR) and artificial neural networks (ANN) is also possible. So, this study is the first detailed evaluation of ensemble models in solar irradiance estimation domain. Boosting and bagging ensembles of SVR, ANN and decision tree (DT), are developed to estimate solar irradiance in hourly basis in five cities in Turkey. First frequently used base models (SVR, ANN, and DT) are created and tested with the use of 5 years meteorological data. Then boosting and bagging ensembles of the base models are developed and tested with the same data. The base models are compared with their ensemble counterparts in terms of average coefficient of determination (R-2) and root mean squared error (RMSE). The comparative results show that boosting and bagging ensemble models improve SVR, ANN, and DT in terms of RMSE between 4.6 and 14.6% in average. The results show empirically that ensemble models improve prediction accuracies of various base regression models and it can be applied to other machine learning models used in solar irradiance prediction.
  • No Thumbnail Available
    Item
    An accurate toponym-matching measure based on approximate string matching
    Kilinç, D
    Approximate string matching (ASM) is a challenging problem, which aims to match different string expressions representing the same object. In this paper, detailed experimental studies were conducted on the subject of toponym matching, which is a new domain where ASM can be performed, and the creation of a single string-matching measure that can perform toponym matching process regardless of the language was attempted. For this purpose, an ASM measure called DAS, which comprises name similarity, word similarity and sentence similarity phases, was created. Considering the experimental results, the retrieval performance and system accuracy of DAS were much better than those of other well-known five measures that were compared on toponym test datasets. In addition, DAS had the best metric values of mean average precision in six languages, and precision/recall graphs confirm this result.
  • No Thumbnail Available
    Item
    THE AVERAGE SCATTERING NUMBER OF GRAPHS
    Aslan, E; Kilinç, D; Yücalar, F; Borandag, E
    The scattering number of a graph is a measure of the vulnerability of a graph. In this paper we investigate a refinement that involves the average of a local version of the parameter. If v is a vertex in a connected graph G, then sc(v)(G) = max{omega(G - S-v) - vertical bar S-v vertical bar},where the maximum is taken over all disconnecting sets S-v of G that contain v. The average scattering number of G denoted by sc(av)(G), is defined as sc(av)(G) = Sigma v is an element of V(G)sc(v)(G)/n, where n will denote the number of vertices in graph G. Like the scattering number itself, this is a measure of the vulnerability of a graph, but it is more sensitive. Next, the relations between average scattering number and other parameters are determined. The average scattering number of some graph classes are obtained. Moreover, some results about the average scattering number of graphs obtained by graph operations are given.
  • No Thumbnail Available
    Item
    TTC-3600: A new benchmark dataset for Turkish text categorization
    Kilinç, D; Özçift, A; Bozyigit, F; Yildirim, P; Yücalar, F; Borandag, E
    Owing to the rapid growth of the World Wide Web, the number of documents that can be accessed via the Internet explosively increases with each passing day. Considering news portals in particular, sometimes documents related to categories such as technology, sports and politics seem to be in the wrong category or documents are located in a generic category called others. At this point, text categorization (TC), which is generally addressed as a supervised learning task is needed. Although there are substantial number of studies conducted on TC in other languages, the number of studies conducted in Turkish is very limited owing to the lack of accessibility and usability of datasets created. In this paper, a new dataset named TTC-3600, which can be widely used in studies of TC of Turkish news and articles, is created. TTC-3600 is a well-documented dataset and its file formats are compatible with well-known text mining tools. Five widely used classifiers within the field of TC and two feature selection methods are evaluated on TTC-3600. The experimental results indicate that the best accuracy criterion value 91.03% is obtained with the combination of Random Forest classifier and attribute ranking-based feature selection method in all comparisons performed after pre-processing and feature selection steps. The publicly available TTC-3600 dataset and the experimental results of this study can be utilized in comparative experiments by other researchers.
  • No Thumbnail Available
    Item
    Systematic literature review of photovoltaic output power forecasting
    Basaran, K; Bozyigit, F; Siano, P; Taser, PY; Kilinç, D
    Since the harmful effects of climate warming on our planet were first observed, the use of renewable energy resources has been significantly increasing. Among the potential renewable energy sources, photovoltaic (PV) system installations keep continuously increasing world-wide due to its economic and environmental contributions. Despite its significant benefits, the inherent variability of PV power generation due to meteorological parameters can cause power management/planning problems. Thus, forecasting of PV output data (directly or indirectly) in an accurate manner is a critical task to provide stability, reliability, and optimisation of the grid systems. In considering the literature reviewed, there are various research items utilizing PV output power forecasting. In this study, a systematic literature review based on the search of primary studies (published between 2010 and 2020), which forecast PV power generation using machine learning and deep learning methods, is reported. The studies are evaluated based on the PV material used, their approaches, generated outputs, data set used, and the performance evaluation methods. As a result, gaps and improvable points in the existing literature are revealed, and suggestions which include novelties are offered for future works.