No abstract

Leukemia is a fatal cancer and has two main types: Acute and chronic. Each type has two more subtypes: Lymphoid and myeloid. Hence, in total, there are four subtypes of leukemia. This study proposes a new approach for diagnosis of all subtypes of leukemia from microscopic blood cell images using convolutional neural networks (CNN), which requires a large training data set. Therefore, we also investigated the effects of data augmentation for an increasing number of training samples synthetically. We used two publicly available leukemia data sources: ALL-IDB and ASH Image Bank. Next, we applied seven different image transformation techniques as data augmentation. We designed a CNN architecture capable of recognizing all subtypes of leukemia. Besides, we also explored other well-known machine learning algorithms such as naive Bayes, support vector machine, k-nearest neighbor, and decision tree. To evaluate our approach, we set up a set of experiments and used 5-fold cross-validation. The results we obtained from experiments showed that our CNN model performance has 88.25% and 81.74% accuracy, in leukemia versus healthy and multiclass classification of all subtypes, respectively. Finally, we also showed that the CNN model has a better performance than other wellknown machine learning algorithms.

The emergence of the Web 2.0 technology generated a massive amount of raw data by enabling Internet users to post their opinions on the web. Processing this raw data to extract useful information can be a very challenging task. An example of important information that can be automatically extracted from the users' posts is their opinions on different issues. This problem of Sentiment Analysis (SA) has been studied well on the English language and two main approaches have been devised: corpus-based and lexicon-based. This work focuses on the later approach due to its various challenges and high potential. The discussions in this paper take the reader through the detailed steps of building the main two components of the lexicon-based SA approach: the lexicon and the SA tool. The experiments show that significant efforts are still needed to reach a satisfactory level of accuracy for the lexicon-based Arabic SA. Nonetheless, they do provide an interesting guide for the researchers in their on-going efforts to improve lexicon-based SA. ENDNOTES1 Some studies include the neutral case as well. 2

The emergence of the Web 2.0 technology generated a massive amount of raw data by enabling Internet users to post their opinions on the web. Processing this raw data to extract useful information can be a very challenging task. An example of important information that can be automatically extracted from the users' posts is their opinions on different issues. This problem of Sentiment Analysis (SA) has been studied well on the English language and two main approaches have been devised: corpus-based and lexicon-based. This work focuses on the later approach due to its various challenges and high potential. The discussions in this paper take the reader through the detailed steps of building the main two components of the lexicon-based SA approach: the lexicon and the SA tool. The experiments show that significant efforts are still needed to reach a satisfactory level of accuracy for the lexicon-based Arabic SA. Nonetheless, they do provide an interesting guide for the researchers in their on-going efforts to improve lexicon-based SA.

Sentiment analysis aims at extracting sentiment embedded mainly in text reviews. The prevalence of semantic web technologies has encouraged users of the web to become authors as well as readers. People write on a wide range of topics. These writings embed valuable information for organizations and industries. This paper introduces a novel framework for sentiment detection in Arabic tweets. The heart of this framework is a sentiment lexicon. This lexicon was built by translating the SentiStrength English sentiment lexicon into Arabic and afterwards the lexicon was expanded using Arabic thesauri. To assess the viability of the suggested framework, the authors have collected and manually annotated a set of 4400 Arabic tweets. These tweets were classified according to their sentiment into positive or negative tweets using the proposed framework. The results reveal that lexicons are helpful for sentiment detection. The overall results are encouraging and open venues for future research. 6 7 8 9 10 11 12 13