Search

The widespread use of the internet today, along with the rapidly increasing information, has brought along great information pollution. it has become a big problem for internet users to obtain meaningful data from this large and noisy data. Text summarization, which is generally used on texts obtained from digital media, has also been used for summarizing scientific articles in different fields. in this study, a scientific text summary study was carried out to be used on Turkish articles written in the field of informatics. A large Turkish Informatics Literature dataset was created with the articles collected from Dergipark. in addition to the text pre-processing studies available in the literature on this dataset, a new original pre-processing function has been developed by the scientific article format. While summarizing, Deep Belief Networks (DBN), which has an increasing use in the field of natural language processing in the literature, has been used. To measure the performance of the developed system, reference summaries were created with the BERT algorithm, which is a pre-trained natural language processing model. After the scientific articles were summarized with BERT and Deep Belief Networks, the abstracts were compared with BERT Score and BART Score, a specialized comparison metric of the BERT Model. The results showed that the developed Turkish informatics Literature Summarization Method constitutes a summary of a scientific article with 0.78 F-Score and 0.68 BART Score in the BERT Score metric. [ABSTRACT FROM AUTHOR]

Nowadays, the Internet is a structure that people can access easily and at the same time produce content easily and without control. In parallel with this situation, the ability of extract information from the raw data that makes up big data has become more complex. The fact that the headlines of the contents contain uncontrolled and misleading elements makes it difficult to reach the right information. The headlines of the contents are important for people to reach the information they want in their limited time. In this study, it is aimed to produce headlines suitable for the content instead of headlines that may be misleading for news. For this purpose, an application that produces headlines for Turkish news with deep learning method has been developed. SuDer news corpus is used as dataset. For the training of the model, it is aimed to obtain more humanoid results in the production of news headlines by using the Transformer architecture, which is frequently preferred in natural language studies today and the abstract summarization method. In this study, in order to compare the performance of the Transformer model, models are prepared and trained with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures. At the end of 25 epochs of training with LSTM, GRU and Transformer architectures on the corpus, the values of loss are 1.03, 0.55 and 2.49 respectively. In the experiments performed on the validation data, measurements are made with ROUGE-1, ROUGE-2 and ROUGE-L metrics. As a result of the measurements, it is observed that the Transformer architecture is partially good, based on the metric values produced. In addition, when the headlines produced with these architectures are examined, it is observed that the headline obtained with the Transformer architecture produce headlines that are partially more suitable for the news content compared to other architectures. [ABSTRACT FROM AUTHOR]

With the advancements in educational technologies, the use of robots in education is becoming increasingly widespread. Around the world, robotic activities and educational programs are being organized to enhance students' cognitive and social skills. However, unfortunately, robot-assisted educational studies and applications for students requiring special education are limited. This research aims to present a humanoid robot-assisted learning environment for children with Down syndrome. In this study, an original dataset for children with Down syndrome has been generated using Turkish natural language processing techniques. This dataset includes special scenarios and a question-answer dataset to assist in improving the cognitive and social skills of the children. The NAO humanoid robot, part of the inventory of Iskenderun Technical University, is prepared to interact with children and use this special dataset. This unique method and dataset aim to create a reciprocal chat environment with children with Down syndrome and improve their focus, attention, concentration, and communication skills. This is an important step as an example of Turkish humanoid robot-assisted education applications in the literature. The next stages of our research will involve using this unique method and dataset with more children with Down syndrome and examining its impacts. This study, which is expected to be an important educational material in terms of improving the communication skills of children who need special education, carries national importance due to being in Turkish and will make significant contributions to special education in our country. [ABSTRACT FROM AUTHOR]

The number of social media users has increased significantly as internet access and internet usage has grown all over the world. As it is the case in any other field, raw data collected from social media platforms are now being transformed into information. Millions of pieces of content are posted every day on platforms such as Twitter, Facebook, and Instagram. Moreover, the ability to extract meaningful information from such content has become an important field of research. This study reports a system for sentiment analysis, based on the data made available on Facebook, Twitter, Instagram, YouTube along with RSS data. Logistic Regression, Random Forest and deep learning algorithm such as Long Short-Term Memory (LSTM) are used to develop the classification model used in the system built as part of this study. Dataset is a new dataset that included data collected from Twitter, used was created and labeled by us. It was found that LSTM model provided the highest accuracy among the models generated using the training dataset. The final version of the model was tested on five different social media platforms and results are communicated.

The number of social media users has increased significantly as internet access and internet usage has grown all over the world. As it is the case in any other field, raw data collected from social media platforms are now being transformed into information. Millions of pieces of content are posted every day on platforms such as Twitter, Facebook, and Instagram. Moreover, the ability to extract meaningful information from such content has become an important field of research. This study reports a system for sentiment analysis, based on the data made available on Facebook, Twitter, Instagram, YouTube along with RSS data. Logistic Regression, Random Forest and deep learning algorithm such as Long Short-Term Memory (LSTM) are used to develop the classification model used in the system built as part of this study. Dataset is a new dataset that included data collected from Twitter, used was created and labeled by us. It was found that LSTM model provided the highest accuracy among the models generated using the training dataset. The final version of the model was tested on five different social media platforms and results are communicated. [ABSTRACT FROM AUTHOR]