Search

It is a fact that technology has made a great contribution to our lives and has a great impact on society. With the development of technology, the amount of data created on the internet has also increased. In particular, social media has turned into an important medium where users can share their beliefs and opinions freely. In this regard, many different sectors have started scrutinizing users’ opinions and emotions with the “opinion mining” method which is one of the fields of Natural Language Processing (NLP). The objective of this paper is to present an approach towards analyzing the community interpreters’ emotions and opinions using “opinion mining” method. In other words, this paper aims at providing a new insight into community interpreting research by introducing opinion mining and sentiment analysis methods, which are mainly used in Computer Science and Management Information Systems. With this aim in mind, the contributions of the opinion mining method to community interpreting research have been discussed with a descriptive approach. [ABSTRACT FROM AUTHOR]

The long jump is defined as an athletic event, and it has also been a standard event in modern Olympic Games. The purpose of the athletes is to make the distance as far as possible from a jumping point. The main purpose of this study was to determine the most successful machine learning algorithm in the prediction of the long jump distance of male athletes. In this paper, we used age and velocity variables for predicting the long jump performance of athletes. During the research, 328 valid jumps belonging to 73 Turkish male athletes were used as data. In determining the most successful algorithm, mean absolute error (MAE), root mean square error (RMSE), Mean Squared Error (MSE), R2 score, Explained Variance Score (EVS), and Mean Squared Logarithmic Error (MSLE) values were taken into consideration. The outcomes of the analysis showed that long jump performance can be determined by chosen independent variables. The 5-fold cross-validation technique was used for the performance evaluation of the models. As a result of the experimental tests, the Gradient Boosting Regression Trees (GBRT) algorithm reached the best result with an MSE value of 0.0865. In this study, it was concluded that the machine learning approach suggested can be used by trainers to determine the long jump performance of male athletes. [ABSTRACT FROM AUTHOR]

Make-up exam is an exam attended by students who fail the course at the end of midterm and general exams and are administered by many universities in our country. Although it is assumed that the students who fail the course will participate in these exams, some of the students may be affected by various internal (low midterm grade, desire to take the course again, need to take a vacation, etc.) and external motivations (distance between hometown and university, financial difficulties, etc.) does not take the make-up exams. Processes such as exam schedules, appointment of invigilators, copy of exam papers and toner, which are made by assuming that all students will take the exam, have caused tangible wastes. In this study, an extreme learning machine-based approach has been proposed in order to determine whether the students who they are expected to join the make-up exam will participate in the make-up exam. In the proposed approach, more than one extreme learning machine have been trained by using samples at a certain rate of the dataset, and the classification have been made with a voting-based approach in the testing phase. Furthermore, the ELM structures those join the voting, have been optimized by artificial bee colony algorithm. The training and testing of the proposed method have been conducted on 10 courses datasets. In the experimental studies, the performance of the extreme learning machine and the proposed method have been compared separately for each dataset, and it is seen that the performance of the proposed method is higher than the basic extreme learning machine in terms of classification accurac. [ABSTRACT FROM AUTHOR]

The fast span of the internet has accelerated the emergence of social media people in all over the world to affect each other in seconds through social media and spread their thoughts quickly. Social media provide an effective communication network individually and organizationally. Users can evaluate the services they have received as consumers or citizens on these platforms as positive or negative. As a result, an interaction network has been formed between the citizens and the organizations they receive services from. Reconsidering this interaction network, citizens frequently interpret municipal services. The services of the municipal corporations, the managing agency, are evaluated by citizens through social media. Considering the public relations aspect, individuals can personally communicate with municipalities and mayors, especially on Twitter. This situation provides a different communication ground between the citizen and the municipality and provides a solution-oriented interaction network. This study covers the Sakarya special; The shares of Twitter users about the Metropolitan Municipality, Adapazarı, Serdivan, Erenler and Hendek municipalities were examined, and the attitudes of citizens towards municipalities were prepared to be analyzed. The texts of tweets sent to municipal accounts were collected. These obtained data were first assigned to predetermined groups with Machine Learning methods, and then Emotion Analysis was performed with the Turkish Bert method, one of the Machine Learning and Deep Learning approaches. Citizens' attitude towards municipalities has emerged and has been evaluated with its positive and negative aspects. With this study, municipalities were provided with positive or negative feedback from citizens, ensuring citizen satisfaction and responding to requests faster. The principal aim to this paper municipalities change the negative attitudes of the citizens positively with the solution-oriented studies they will do. It is thought that through Twitter, municipalities will contribute to the society with topics such as improving their bilateral dialogue with citizens, finding solutions to requests, demands and complaints, and strengthening participatory democracy. [ABSTRACT FROM AUTHOR]

Language identification (LI), which is a major task in natural language processing, is the process of determining the language from a given content. In this paper, a novel approach, which is based on the probability of the use of the characters that have the similar orders with respect to their UTF-8 values, was proposed. In order to evaluate and validate the proposed approach, four datasets, which contain texts in different numbers of languages, were employed. In the proposed approach, the features that were exacted by one-dimensional local binary pattern (1D-LBP) method were classified by various machine learning methods. Achieved LI accuracies in each of four employed datasets were 86.20%, 92.75%, 100% and 89.77%, respectively. The results showed that the proposed approach yields high success rates and it is an efficient way of language identification. [ABSTRACT FROM AUTHOR]

Recently, the Extreme Learning Machine (ELM) becomes an interesting topic in machine learning area. The ELM has been proposed as a new learning algorithm for Single-Hidden Layer Feed forward Networks (SLFNs). The ELM structure has several advantageous such as good generalization performance, extremely fast learning ability and low computational process. Besides this advantageous, the ELM structure has some drawbacks. Firstly, the ELM encounters over-fitting problems because of using a least squares minimization in calculation of the output weights. The other drawback is about accuracy of the ELM. It depends on the number of hidden neurons. This situation is a big challenge in high-dimensional problems for some practical applications. In this paper, we propose a sparse ELM model to overcome the above-mentioned drawbacks. In the sparse ELM model, Forward-Backward Pursuit (FBP) algorithms based on greedy pursuit was used to obtain sparse representation of the output weights. The proposed method which is called FBP-ELM, has several benefits in comparing with the traditional ELM schemes such as avoiding over-fitting, low computational complexity and with adequate number of neurons in hidden layer. FBP-ELM shows its remarkable advantages when it is compared with the empirical studies on commonly used classification benchmarks. Moreover, a comparison with the original ELM and the other regularized ELM schemes such as Least-angle regression (LARS), Least absolute shrinkage and selection operator (LASSO) and Elastic Net is presented to show effectiveness of proposed FBP-ELM method. [ABSTRACT FROM AUTHOR]

The classification of observations is an important constituent of statistics and machine learning, either for analysis of data sets, or as a subgoal of a more complex problem. A novel machine learning technique, Support Vector Machines (SVM), has recently been receiving considerable attention in pattern recognition and regression function estimation problems. This paper uses standard logistic regression models for binary classification problems and compares them with SVM models with linear and non-linear kernel functions. An application with real data associated with giving birth to a low birth weight baby and patients with cancer of prostate are presented as an illustration. Based on the results of the numerical examples, it is determined that Support Vector Classification method produces remarkable results. [ABSTRACT FROM AUTHOR]