No abstract

The purpose of automated health surveillance systems is to predict the emergence of a disease. In most cases, these systems use a text categorization model to classify any clinical text into a category corresponding to an illness. The problem arises when the target classes refer to diseases sharing multiple information such as symptoms. Thus, the classifier will have difficulty discriminating the disease under surveillance from other conditions of the same family, causing an increase in misclassification rate. Clinical texts contain keywords carrying relevant information to distinguish diseases with similar symptoms. However, these specific words are rare and sparse. Therefore, they have a minor impact on machine learning models' performance. Assuming that emphasizing specific terms contributes to improving classification performance, we propose an algorithm that enriches training samples with terms semantically similar to specific terms using the deep contextualized word embeddings ELMo. Next, we devise a weighting scheme combining chi-square and semantic scores to reflect the relatedness between features and the disease under surveillance. We evaluate our model using the SVM algorithm trained on i2b2 dataset supplemented by documents collected from Ibn Sina hospital in Rabat. Experimental results show a clear improvement in classification performance than baseline methods with an F-measure reaching 86.54%.

<p><span lang="EN-US">Nowadays, mining user reviews becomes a very useful mean for decision making in several areas. Traditionally, machine learning algorithms have been widely and effectively used to analyze user’s opinions on a limited volume of data. In the case of massive data, powerful hardware resources (CPU, memory, and storage) are essential for dealing with the whole data processing phases including, collection, pre-processing, and learning in an optimal time. Several big data technologies have emerged to efficiently process massive data, like Apache Spark, which is a distributed framework for data processing that provides libraries implementing several machine learning algorithms. In order to evaluate the performance of Apache Spark's machine learning library (MLlib) on a large volume of data, classification accuracies and processing time of two machine learning algorithms implemented in spark: naive </span><span>B</span><span lang="EN-US">ayes and support vector machine (SVM) are compared to the performance achieved by the standard implementation of these two algorithms on large different size datasets built from movie reviews. The results of our experiment show that the performance of classifiers running under spark is higher than traditional ones and reaches F-measure greater than 84%. At the same time, we found that under spark framework, the learning time is relatively low.</span></p>

Traditionally, pharmacovigilance data are collected during clinical trials on a small sample of patients and are therefore insufficient to adequately assess drugs. Nowadays, consumers use online drug forums to share their opinions and experiences about medication. These feedbacks, which are widely available on the web, are automatically analyzed to extract relevant information for decision-making. Currently, sentiment analysis methods are being put forward to leverage consumers' opinions and produce useful drug monitoring indicators. However, these methods' effectiveness depends on the quality of word representation, which presents a real challenge because the information contained in user reviews is noisy and very subjective. Over time, several sentiment classification problems use machine learning methods based on the traditional bag of words model, sometimes enhanced with lexical resources. In recent years, word embedding models have significantly improved classification performance due to their ability to capture words' syntactic and semantic properties. Unfortunately, these latter models are weak in sentiment classification tasks because they are unable to encode sentiment information in the word representation. Indeed, two words with opposite polarities can have close word embeddings as they appear together in the same context. To overcome this drawback, some studies have proposed refining pre-trained word embeddings with lexical resources or learning word embeddings using training data. However, these models depend on external resources and are complex to implement. This work proposes a deep contextual word embeddings model called ELMo that inherently captures the sentiment information by providing separate vectors for words with opposite polarities. Different variants of our proposed model are compared with a benchmark of pre-trained word embeddings models using SVM classifier trained on Drug Review Dataset. Experimental results show that ELMo embeddings improve classification performance in sentiment analysis tasks on the pharmaceutical domain.