Evaluating and improving morpho-syntactic classification over multiple corpora using pre-trained, "off-the-shelf", parts-of-speech tagging tools

This paper evaluates six commonly available parts-of-speech tagging tools over corpora other than those upon which they were originally trained. In particular this investigation measures the performance of the selected tools over varying styles and genres of text without retraining, under the assumption that domain specific training data is not always available. An investigation is performed to determine whether improved results can be achieved by combining the set of tagging tools into ensembles that use voting schemes to determine the best tag for each word. It is found that while accuracy drops due to non-domain specific training, and tag-mapping between corpora, accuracy remains very high, with the support vector machine-based tagger, and the decision tree-based tagger performing best over different corpora. It is also found that an ensemble containing a support vector machine-based tagger, a probabilistic tagger, a decision-tree based tagger and a rule-based tagger produces the largest increase in accuracy and the largest reduction in error across different corpora, using the Precision-Recall voting scheme.

Evaluating and improving morpho-syntactic classification over multiple corpora using pre-trained, “off-the-shelf”, parts-of-speech tagging tools

his paper evaluates six commonly available parts-of-speech tagging tools over corpora other than those upon which they were originally trained. In particular this investigation measures the performance of the selected tools over varying styles and genres of text without retraining, under the assumption that domain specific training data is not always available. An investigation is performed to determine whether improved results can be achieved by combining the set of tagging tools into ensembles that use voting schemes to determine the best tag for each word. It is found that while accuracy drops due to non-domain specific training, and tag-mapping between corpora, accuracy remains very high, with the support vector machine-based tagger, and the decision tree-based tagger performing best over different corpora. It is also found that an ensemble containing a support vector machine-based tagger, a probabilistic tagger, a decision-tree based tagger and a rule-based tagger produces the largest increase in accuracy and the largest reduction in error across different corpora, using the Precision-Recall voting scheme.

Improving reliability of unbalanced text mining by reducing performance bias

Class imbalance in textual data is one important factor that affects the reliability of text mining. For imbalanced textual data, conventional classifiers tend to have a strong performance bias, which results in high accuracy rate on the majority class but very low rate on the minorities. An extreme strategy for unbalanced learning is to discard the majority instances and apply one-class classification to the minority class. However, this could easily cause another type of bias, which increases the accuracy rate on minorities by sacrificing the majorities. This chapter aims to investigate approaches that reduce these two types of performance bias and improve the reliability of discovered classification rules. Experimental results show that the inexact field learning method and parameter optimized one class classifiers achieve more balanced performance than the standard approaches.

Prediction of age, sentiment, and connectivity from social media text

Social media corpora, including the textual output of blogs, forums, and messaging applications, provide fertile ground for linguistic analysis material diverse in topic and style, and at Web scale. We investigate manifest properties of textual messages, including latent topics, psycholinguistic features, and author mood, of a large corpus of blog posts, to analyze the impact of age, emotion, and social connectivity. These properties are found to be significantly different across the examined cohorts, which suggest discriminative features for a number of useful classification tasks. We build binary classifiers for old versus young bloggers, social versus solo bloggers, and happy versus sad posts with high performance. Analysis of discriminative features shows that age turns upon choice of topic, whereas sentiment orientation is evidenced by linguistic style. Good prediction is achieved for social connectivity using topic and linguistic features, leaving tagged mood a modest role in all classifications.

Classification and optimization of product review information using soft computing models

A soft computing framework to classify and optimize text-based information extracted from customers' product reviews is proposed in this paper. The soft computing framework performs classification and optimization in two stages. Given a set of keywords extracted from unstructured text-based product reviews, a Support Vector Machine (SVM) is used to classify the reviews into two categories (positive and negative reviews) in the first stage. An ensemble of evolutionary algorithms is deployed to perform optimization in the second stage. Specifically, the Modified micro Genetic Algorithm (MmGA) optimizer is applied to maximize classification accuracy and minimize the number of keywords used in classification. Two Amazon product reviews databases are employed to evaluate the effectiveness of the SVM classifier and the ensemble of MmGA optimizers in classification and optimization of product related keywords. The results are analyzed and compared with those published in the literature. The outputs potentially serve as a list of impression words that contains useful information from the customers' viewpoints. These impression words can be further leveraged for product design and improvement activities in accordance with the Kansei engineering methodology.

Classification ensemble to improve medical named entity recognition

An accurate Named Entity Recognition (NER) is important for knowledge discovery in text mining. This paper proposes an ensemble machine learning approach to recognise Named Entities (NEs) from unstructured and informal medical text. Specifically, Conditional Random Field (CRF) and Maximum Entropy (ME) classifiers are applied individually to the test data set from the i2b2 2010 medication challenge. Each classifier is trained using a different set of features. The first set focuses on the contextual features of the data, while the second concentrates on the linguistic features of each word. The results of the two classifiers are then combined. The proposed approach achieves an f-score of 81.8%, showing a considerable improvement over the results from CRF and ME classifiers individually which achieve f-scores of 76% and 66.3% for the same data set, respectively.

New markov chain based methods for single and cross-domain sentiment classification

Nowadays communication is switching from a centralized scenario, where communication media like newspapers, radio, TV programs produce information and people are just consumers, to a completely different decentralized scenario, where everyone is potentially an information producer through the use of social networks, blogs, forums that allow a real-time worldwide information exchange. These new instruments, as a result of their widespread diffusion, have started playing an important socio-economic role. They are the most used communication media and, as a consequence, they constitute the main source of information enterprises, political parties and other organizations can rely on. Analyzing data stored in servers all over the world is feasible by means of Text Mining techniques like Sentiment Analysis, which aims to extract opinions from huge amount of unstructured texts. This could lead to determine, for instance, the user satisfaction degree about products, services, politicians and so on. In this context, this dissertation presents new Document Sentiment Classification methods based on the mathematical theory of Markov Chains. All these approaches bank on a Markov Chain based model, which is language independent and whose killing features are simplicity and generality, which make it interesting with respect to previous sophisticated techniques. Every discussed technique has been tested in both Single-Domain and Cross-Domain Sentiment Classification areas, comparing performance with those of other two previous works. The performed analysis shows that some of the examined algorithms produce results comparable with the best methods in literature, with reference to both single-domain and cross-domain tasks, in $2$-classes (i.e. positive and negative) Document Sentiment Classification. However, there is still room for improvement, because this work also shows the way to walk in order to enhance performance, that is, a good novel feature selection process would be enough to outperform the state of the art. Furthermore, since some of the proposed approaches show promising results in $2$-classes Single-Domain Sentiment Classification, another future work will regard validating these results also in tasks with more than $2$ classes.

An ERP study of major-minor classification in melodies

COMPOSERS COMMONLY USE MAJOR OR MINOR SCALES to create different moods in music.Nonmusicians show poor discrimination and classification of this musical dimension; however, they can perform these tasks if the decision is phrased as happy vs. sad.We created pairs of melodies identical except for mode; the first major or minor third or sixth was the critical note that distinguished major from minor mode. Musicians and nonmusicians judged each melody as major vs. minor or happy vs. sad.We collected ERP waveforms, triggered to the onset of the critical note. Musicians showed a late positive component (P3) to the critical note only for the minor melodies, and in both tasks.Nonmusicians could adequately classify the melodies as happy or sad but showed little evidence of processing the critical information. Major appears to be the default mode in music, and musicians and nonmusicians apparently process mode differently.

Mining for Class-Specific Motifs in Protein Sequence Classification

Background: In protein sequence classification, identification of the sequence motifs or n-grams that can precisely discriminate between classes is a more interesting scientific question than the classification itself. A number of classification methods aim at accurate classification but fail to explain which sequence features indeed contribute to the accuracy. We hypothesize that sequences in lower denominations (n-grams) can be used to explore the sequence landscape and to identify class-specific motifs that discriminate between classes during classification. Discriminative n-grams are short peptide sequences that are highly frequent in one class but are either minimally present or absent in other classes. In this study, we present a new substitution-based scoring function for identifying discriminative n-grams that are highly specific to a class. Results: We present a scoring function based on discriminative n-grams that can effectively discriminate between classes. The scoring function, initially, harvests the entire set of 4- to 8-grams from the protein sequences of different classes in the dataset. Similar n-grams of the same size are combined to form new n-grams, where the similarity is defined by positive amino acid substitution scores in the BLOSUM62 matrix. Substitution has resulted in a large increase in the number of discriminatory n-grams harvested. Due to the unbalanced nature of the dataset, the frequencies of the n-grams are normalized using a dampening factor, which gives more weightage to the n-grams that appear in fewer classes and vice-versa. After the n-grams are normalized, the scoring function identifies discriminative 4- to 8-grams for each class that are frequent enough to be above a selection threshold. By mapping these discriminative n-grams back to the protein sequences, we obtained contiguous n-grams that represent short class-specific motifs in protein sequences. Our method fared well compared to an existing motif finding method known as Wordspy. We have validated our enriched set of class-specific motifs against the functionally important motifs obtained from the NLSdb, Prosite and ELM databases. We demonstrate that this method is very generic; thus can be widely applied to detect class-specific motifs in many protein sequence classification tasks. Conclusion: The proposed scoring function and methodology is able to identify class-specific motifs using discriminative n-grams derived from the protein sequences. The implementation of amino acid substitution scores for similarity detection, and the dampening factor to normalize the unbalanced datasets have significant effect on the performance of the scoring function. Our multipronged validation tests demonstrate that this method can detect class-specific motifs from a wide variety of protein sequence classes with a potential application to detecting proteome-specific motifs of different organisms.

Classification and selection of biomarkers in genomic data using LASSO

High-throughput gene expression technologies such as microarrays have been utilized in a variety of scientific applications. Most of the work has been on assessing univariate associations between gene expression with clinical outcome (variable selection) or on developing classification procedures with gene expression data (supervised learning). We consider a hybrid variable selection/classification approach that is based on linear combinations of the gene expression profiles that maximize an accuracy measure summarized using the receiver operating characteristic curve. Under a specific probability model, this leads to consideration of linear discriminant functions. We incorporate an automated variable selection approach using LASSO. An equivalence between LASSO estimation with support vector machines allows for model fitting using standard software. We apply the proposed method to simulated data as well as data from a recently published prostate cancer study.

Classification Using Generalized Partial Least Squares

The advances in computational biology have made simultaneous monitoring of thousands of features possible. The high throughput technologies not only bring about a much richer information context in which to study various aspects of gene functions but they also present challenge of analyzing data with large number of covariates and few samples. As an integral part of machine learning, classification of samples into two or more categories is almost always of interest to scientists. In this paper, we address the question of classification in this setting by extending partial least squares (PLS), a popular dimension reduction tool in chemometrics, in the context of generalized linear regression based on a previous approach, Iteratively ReWeighted Partial Least Squares, i.e. IRWPLS (Marx, 1996). We compare our results with two-stage PLS (Nguyen and Rocke, 2002A; Nguyen and Rocke, 2002B) and other classifiers. We show that by phrasing the problem in a generalized linear model setting and by applying bias correction to the likelihood to avoid (quasi)separation, we often get lower classification error rates.

INVESTIGATION OF AIR JIGGING AND AIR CLASSIFICATION TO RECOVER METALLIC PARTICLES FROM ANALYTICAL SAMPLES

Analyzing “nuggety” gold samples commonly produces erratic fire assay results, due to random inclusion or exclusion of coarse gold in analytical samples. Preconcentrating gold samples might allow the nuggets to be concentrated and fire assayed separately. In this investigation synthetic gold samples were made using similar density tungsten powder and silica, and were preconcentrated using two approaches: an air jig and an air classifier. Current analytical gold sampling method is time and labor intensive and our aim is to design a set-up for rapid testing. It was observed that the preliminary air classifier design showed more promise than the air jig in terms of control over mineral recovery and preconcentrating bulk ore sub-samples. Hence the air classifier was modified with the goal of producing 10-30 grams samples aiming to capture all of the high density metallic particles, tungsten in this case. Effects of air velocity and feed rate on the recovery of tungsten from synthetic tungsten-silica mixtures were studied. The air classifier achieved optimal high density metal recovery of 97.7% at an air velocity of 0.72 m/s and feed rate of 160 g/min. Effects of density on classification were investigated by using iron as the dense metal instead of tungsten and the recovery was seen to drop from 96.13% to 20.82%. Preliminary investigations suggest that preconcentration of gold samples is feasible using the laboratory designed air classifier.