Search

Sentiment analysis is one of the sub-domains of Natural Language Processing (NLP) that is of piqued interest in the research community. With the advent of e-commerce and social media, more and more customer opinions are being provided online in the written text form. Nowadays, sentiment analysis provides a way for companies to understand customer opinions towards products and services in a global marketplace. Negative sentences or using negations in sentences have a significant impact on sentiment polarity detection. Inappropriate processing of negations in leads to biases and misclassification of sentiments. In this paper, we provide a novel end-to-end sentiment analysis approach to handle negations, along with the inclusion of negation identification and negation scope marking. Our approach introduces a customized negation marking algorithm for explicit negation detection and perform experiments on sentiment analysis with different machine learning algorithms such as Naïve Bayes, Support Vector Machines, Artificial Neural Network (ANN), and Recurrent Neural Network (RNN) on sentiment analysis of Amazon reviews, specifically of cell phones. By evaluating the effect of the negation algorithm on the sentiment analysis tasks, the RNN achieved the best accuracy of 95.67% when combined with our negation marking processing, exceeding its accuracy without any identification of negative sentences. Further, our approach was applied to another dataset of Amazon reviews and demonstrated a significant improvement in the overall accuracy. [ABSTRACT FROM AUTHOR]

This study compares disease classification based on landmark and non-landmark gene expression data, and clinical variable using multiple machine-learning models. The influence of the number of principal components and the genes were also investigated. The results indicate that the ANN model has the best accuracy for disease type prediction among all the models, model using 95 principal components has better accuracy than that of 25 principal components, and the greater number of genes used, the higher the prediction accuracy. Models using landmark genes demonstrated better accuracy than the models using non-landmark genes especially with 95 PCs across all the models except for the decision trees. The optimal model was one that uses landmark genes with 95 PCs as features for an ANN classifier. The AUC measures obtained on the test set were 0.98,0.98,1 and 0.96 for Autoimmune, Bacteremia, Cancer and Healthy classes respectively, and the accuracy for the respective classes were 97.56%, 95.65%, 95.65%, and 58.82%. The ANN model demonstrated a good capability of distinguishing between the true positives and the false positives, and it resulted in high prediction accuracy for the 3 disease classes (Autoimmune, Bacteremia, Cancer), but it misclassified some instances from the Healthy class to the Autoimmune and Bacteremia class, likely due to a wide range of gene expression level for the Healthy class. [ABSTRACT FROM AUTHOR]

The L1000 dataset, containing gene microarray data from 978 landmark genes has been previously shown to accurately predict expression of ~81% of the remaining 21,290 target genes. Microarray data was utilized to characterize groups of tissue types within the L1000 dataset to assess whether 978 landmark genes, compared to non-landmark genes, would better differentiate samples into clusters containing distinct tissue types. Landmark genes better differentiated k-means clusters, compared to non-landmark genes. These results suggest that landmark genes better characterize heterogeneous samples in their comprehensive genetic profile. Our previous studies showed that categorical separation of samples based on clinical or biological groups generally improves when studying heterogeneous sample types when using landmark genes as features, compared to non-landmark genes. However, the present work indicates that non-landmark genes may also be utilized to separate samples in clustering when there is a large sample size present for training k-means clustering models. In contrast, when studying a small sample size of the same set of heterogenous samples, landmark genes as features improve clustering. This study has implications for assessing various tissue types as landmark genes may be directly measured to predict categorical sample qualities as well as expression of remaining target genes. [ABSTRACT FROM AUTHOR]

This work proposes a data-driven model that uses data on natural disasters from the National Oceanic and Atmospheric Administration (NOAA) to enable predictive analytics and simulation of disruptions caused by natural hazards. Random generation of disruption is something that would be simple to implement. Still, it might not help researchers/policy-makers test the resilience from the occurrence of a natural disaster standpoint. Natural hazards such as a hurricane, tornado, or tropical storm are usually uncertain to predict unless we deploy a complex prediction algorithm that takes different atmospheric variables into account. Rather than diving into the meteorological predictive techniques, a data-driven model is proposed using the apriori algorithm to rely on historical data. Historical data-based techniques help generate disruption scenarios based on their historical occurrence and their topographical propagation. This, in turn, gives us disruptions that are historically significant and possible from their occurrence perspective. [ABSTRACT FROM AUTHOR]

Dimensionality reduction methods such as principal component analysis (PCA) are used to select relevant features, and k-means clustering performs well when applied to data with low effective dimensionality. This study integrated PCA and k-means clustering using the L1000 dataset, containing gene microarray data from 978 landmark genes, which have been previously shown to predict expression of ~81% of the remaining 21,290 target genes with low error. Groups within the L1000 dataset were characterized using both microarray and clinical metadata to assess whether 978 landmark genes would improve clustering results, compared to a random set of 978 genes. The role of clinical variables, including morphological diagnosis, were assessed across k-means clustering groups within homogeneous tissue samples in the L1000 dataset. Results show that the 978 landmark genes better differentiated k-means clusters, relative to 978 randomly selected non-landmark genes. K-means clusters generated from the landmark genes showed more separation of cluster groups when plotted against the first two principal components, which capture a greater proportion of variation for the 978 landmark genes. These results suggest that the 978 landmark genes better represent the overall genetic profile of these heterogeneous samples. Future studies will implement predictive analytics techniques to further investigate the interaction of microarray data and clinical variables such as cancer stage. [ABSTRACT FROM AUTHOR]

Survival outcomes were assessed in cancer patients from whom cancer tissue was analyzed with Illumina Hi-Seq ribonucleic acid (RNA) sequencing (RNA-Seq) (accessible on National Cancer Institute Genomic Data Commons (GDC) and The Cancer Genome Atlas (TCGA)). Cancer-relevant genes with the most significant correlations with the clinical outcome of overall survival were assessed in Kaplan Meier survival analysis plots. In addition, clinical variables as well as the interaction of clinical variables and cancer relevant genes were assessed in survival analysis. Results show that TP53, BRCA1, NBN, MADIL1, and EP300 were significant predictors of overall survival for prostate cancer patients. While these genes and clinical variables (Gleason Score group and biochemical recurrence) were significant predictors of overall survival when assessed separately, the combination of gene levels along with Gleason score groups provided the most predictive power for overall survival. In this study, cancer-relevant genes predicted survival outcomes, although various genes may interact with genes currently known to contribute to cancer. These findings indicate that multiple cancer types should be assessed together to determine which genes are relevant for cancer in general and for specific cancer types. Future studies will assess all RNA sequencing results available on the Genomic Data Commons, including those not yet associated with cancer. These findings have implications for assessing gene-gene interactions and gene-environment interactions prostate cancer as well as for other types of cancer. [ABSTRACT FROM AUTHOR]

Emotion classification deals with identifying emotions expressed within a text. Social media is generating a vast amount of emotion rich data in the form of tweets, status updates, blog posts etc. Tweets are a good representative of emotions a person usually expresses publicly. By analyzing the emotions in these tweets, one can get an idea of how a person feels about the subject they are referring to. Machine Learning (ML) techniques are widely used for analyzing emotions within the tweets. However, there are no balanced training datasets that can be used for training the ML classifiers. As a result, supervised classifiers demonstrate a poor performance with classifying emotions within texts particularly within the tweets. In addition to that, none of the available datasets are useful for training the classifiers to identify and classify emotions within the tweets. Therefore, in this paper we have proposed a novel approach for constructing a balanced heterogeneous training dataset for emotion classification of the tweets. Using the lexicon-based NRC classifier we have classified the textual instances in to four different emotions such as joyful, sad, angry and surprise. Using this as a training dataset we have trained six different machine learning models including the Multiclass Logistic Regression (MLR), Multinomial Naïve Bayes (MLB), Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). Our study reveals that this approach has the potentiality in boosting the performance of the supervised classifiers for emotion classification within the tweets. [ABSTRACT FROM AUTHOR]

Abstract Identification of important activities in a process architecture is a complex task. This paper takes a network perspective approach: Process architectures are represented as activity networks and are modelled as a Discrete-Time Markov Chain (DTMC). Here we propose a DTMC-based component ranking method (Markov chain) to rank important activities in a variety of process architectures of complex system development projects. Analysis of the results show that the proposed model possesses the capability to highly rank critical activities in a process architecture that are capable of either leading to task volatility i.e. increase the probability of rework, have the tendency to cause large iteration cycles, posing a high risk to the process in terms of delay and failure, or leading to unplanned rework. The results are also compared with other widely used network metrics, namely, closeness, betweenness and eigenvector centrality. In our pilot study on four different process architectures, Markov chain outperformed other ranking strategies in highly ranking the significant activities of the process architecture. [ABSTRACT FROM AUTHOR]