Emoji prediction is an important research task that focuses on finding the most appropriate emoji(s) quickly and effortlessly for a specific text. Now that Turkish is on the list of the top 20 most spoken languages in the world and there are a considerable number of Turkish-speaking social media users, studying emoji prediction in Turkish holds significant value. In this study, a Turkish tweets database, named Bitirim's Turkish Tweets Database (B-TTDb), was constructed for academic and industrial studies based on the prediction of the top 100 emojis. B-TTDb consists of four datasets. The first dataset includes raw tweets, the second dataset is the organized version of the first dataset, the third dataset is the pre-processed version of the second dataset, and the last one is the organized version of the third dataset. The last one is the final version, and it is named Bitirim's Dataset (B-D). It includes a total of 158,201 unique tweets belonging to the top 100 emoji classes. For database validation, experiments were conducted on B-D with popular machine learning algorithms for the top 10, 20, 50, and 100 emojis. This study could be considered as the first study that contributes to the literature by the first validated large database of Turkish tweets that includes such a large number of emojis. In addition, B-TTDb could be a basis as well as motivation for various further studies.

This study investigates reverse image search performance of Google, in terms of Average Precisions (APs) at various cut-off points, on finding out similar images by using fresh Image Queries (IQs) from the five categories "Fashion", "Computer", "Home", "Sports", and "Toys", in order to have an insight about reverse image search performance of Google and then, motivate the researchers and inform the users. Five fresh IQs with different main concepts were created for each of the five categories. These 25 IQs were run on the search engine and for each, the first 100 images retrieved were evaluated with binary relevance judgment. APs at the cut-off points 20, 40, 60, 80, and 100 were calculated for each category and for all 25 IQs. The performance range is from ~42% for Toys category at the cut-off point 100 to 71% for Home category at the cut-off point 20. When the categories are ignored, Google's performance range is from ~52% at the cut-off point 100 to ~57% at the cut-off point 20. It seems that reverse image search performance of Google needs to be improved.

Obesity is a public health problem that has become widespread worldwide. Obesity may increase the risk for many health problems such as early puberty, Type 2 diabetes, certain types of cancer, high blood pressure, heart diseases, and sleep apnea. The detection of obesity in children and adolescents at early stages is important and it is crucial to start individual based treatments. Due to the widespread use of smart mobile devices among family members and increasing number of m-Health applications to fight against obesity as well as other diseases, m-Health applications can be a good choice for early detection of obesity in childhood and adolescence stages. Recently, many studies about mobile-based obesity tracking system that mostly for adults have been done. This research study especially emphases obesity management in childhood and adolescence stages with the contribution of Semantic Web technology. Therefore, the system is an ontology-based obesity tracking system for children and adolescents which has its own Obesity Tracking Ontology and medical semantic rule knowledge base with an inference engine.

This article proposes an Intelligent Tracking System for Acute Respiratory Tract Infection (TrackARTI) via a smart mobile for monitoring disease term of 0-6 age group child patients remotely (e.g. home, clinics). It is possible to maximize the quality of life of the child patients and decrease parental anxiety by keeping the child under control during monitoring stage and achieve a proper distant diagnose by the patient's clinician. This is possible with the designs of intelligent M-Health systems that can be used for diagnosing and monitoring the child patients away from hospitals by presenting the instant medical data to their registered doctors. Intelligent M-Health systems require strong knowledge management technology and ease of extension to provide information from additional medical tools. With the contribution of intelligent M-Health systems, it is possible to infer new facts from the certain gathered medical data during examination from child patients. This article mentions an intelligent and easy medical data gathering system that can be used by pediatricians or parents any time. In addition, the system has its own inferencing mechanism that involves two main steps, inferencing on image processing and Semantic Web rule knowledge base.

This article investigates the information retrieval performance of popular search engines on finding Turkish documents. First of all, five popular search engines (Google, Yahoo, Msn, All the Web and Ask) and a list of Turkish queries are determined. Each query is run on each search engine one by one and first twenty documents on each retrieval output are evaluated as being 'relevant' and 'non-relevant'. Then, for evaluation of search engines precision and normalized recall ratios are calculated at various cut-off points for each query and search engine. Furthermore, the results are used to make comparison of the search engines with local search engines. Overall,-Google appears to be the best search engine in terms of average precision (73%) and normalized recall ratios (66%), on finding Turkish documents. However, local search engines have lower information retrieval performance to finding Turkish documents and need more improvement than international search engines.

In this article, the impact of increasing number of query words on information retrieval effectiveness of image search engines is investigated. First of all, four popular search engines, namely Google, Yahoo, Msn, and Ask are selected. Then, forty queries are extracted from the list of Wordtracker and categorized in four groups as one-word, two-word, three-word and four-word queries. After every query is run on the selected image search engines and binary human relevance judgment is done on first twenty image items retrieved, the performance evaluation of image search engines are done in terms of precision and normalized recall. Overall, Google appears to be the best image search engine. The information retrieval effectiveness of image search engines decreases, when the number of query words increases. Therefore, image search engines still need to be improved.