Learning higher-level features with convolutional restricted Boltzmann machines for sentiment analysis

In recent years, learning word vector representations has attracted much interest in Natural Language Processing. Word representations or embeddings learned using unsupervised methods help addressing the problem of traditional bag-of-word approaches which fail to capture contextual semantics. In this paper we go beyond the vector representations at the word level and propose a novel framework that learns higher-level feature representations of n-grams, phrases and sentences using a deep neural network built from stacked Convolutional Restricted Boltzmann Machines (CRBMs). These representations have been shown to map syntactically and semantically related n-grams to closeby locations in the hidden feature space. We have experimented to additionally incorporate these higher-level features into supervised classifier training for two sentiment analysis tasks: subjectivity classification and sentiment classification. Our results have demonstrated the success of our proposed framework with 4% improvement in accuracy observed for subjectivity classification and improved the results achieved for sentiment classification over models trained without our higher level features.

A rule-based approach to implicit emotion detection in text

Most research in the area of emotion detection in written text focused on detecting explicit expressions of emotions in text. In this paper, we present a rule-based pipeline approach for detecting implicit emotions in written text without emotion-bearing words based on the OCC Model. We have evaluated our approach on three different datasets with five emotion categories. Our results show that the proposed approach outperforms the lexicon matching method consistently across all the three datasets by a large margin of 17–30% in F-measure and gives competitive performance compared to a supervised classifier. In particular, when dealing with formal text which follows grammatical rules strictly, our approach gives an average F-measure of 82.7% on “Happy”, “Angry-Disgust” and “Sad”, even outperforming the supervised baseline by nearly 17% in F-measure. Our preliminary results show the feasibility of the approach for the task of implicit emotion detection in written text.

The n-tuple classifier: too good to ignore

The n-tuple pattern recognition method has been tested using a selection of 11 large data sets from the European Community StatLog project, so that the results could be compared with those reported for the 23 other algorithms the project tested. The results indicate that this ultra-fast memory-based method is a viable competitor with the others, which include optimisation-based neural network algorithms, even though the theory of memory-based neural computing is less highly developed in terms of statistical theory.

Benchmarking the n-tuple classifier with statlog dataset

The n-tuple recognition method was tested on 11 large real-world data sets and its performance compared to 23 other classification algorithms. On 7 of these, the results show no systematic performance gap between the n-tuple method and the others. Evidence was found to support a possible explanation for why the n-tuple method yields poor results for certain datasets. Preliminary empirical results of a study of the confidence interval (the difference between the two highest scores) are also reported. These suggest a counter-intuitive correlation between the confidence interval distribution and the overall classification performance of the system.

Good-turing estimation for the frequentist n-tuple classifier

We present results concerning the application of the Good-Turing (GT) estimation method to the frequentist n-tuple system. We show that the Good-Turing method can, to a certain extent rectify the Zero Frequency Problem by providing, within a formal framework, improved estimates of small tallies. We also show that it leads to better tuple system performance than Maximum Likelihood estimation (MLE). However, preliminary experimental results suggest that replacing zero tallies with an arbitrary constant close to zero before MLE yields better performance than that of GT system.

A theoretical and experimental account of n-tuple classifier performance

The n-tuple recognition method is briefly reviewed, summarizing the main theoretical results. Large-scale experiments carried out on Stat-Log project datasets confirm this method as a viable competitor to more popular methods due to its speed, simplicity, and accuracy on the majority of a wide variety of classification problems. A further investigation into the failure of the method on certain datasets finds the problem to be largely due to a mismatch between the scales which describe generalization and data sparseness.

Semi-supervised construction of general visualization hierarchies

We have recently developed a principled approach to interactive non-linear hierarchical visualization [8] based on the Generative Topographic Mapping (GTM). Hierarchical plots are needed when a single visualization plot is not sufficient (e.g. when dealing with large quantities of data). In this paper we extend our system by giving the user a choice of initializing the child plots of the current plot in either interactive, or automatic mode. In the interactive mode the user interactively selects ``regions of interest'' as in [8], whereas in the automatic mode an unsupervised minimum message length (MML)-driven construction of a mixture of GTMs is used. The latter is particularly useful when the plots are covered with dense clusters of highly overlapping data projections, making it difficult to use the interactive mode. Such a situation often arises when visualizing large data sets. We illustrate our approach on a data set of 2300 18-dimensional points and mention extension of our system to accommodate discrete data types.

Semi-supervised learning of hierarchical latent trait models for data visualisation

An interactive hierarchical Generative Topographic Mapping (HGTM) ¸iteH_GTM has been developed to visualise complex data sets. In this paper, we build a more general visualisation system by extending the HGTM visualisation system in 3 directions: bf (1) We generalize HGTM to noise models from the exponential family of distributions. The basic building block is the Latent Trait Model (LTM) developed in ¸iteKaban_pami. bf (2) We give the user a choice of initializing the child plots of the current plot in either em interactive, or em automatic mode. In the interactive mode the user interactively selects ``regions of interest'' as in ¸iteH_GTM, whereas in the automatic mode an unsupervised minimum message length (MML)-driven construction of a mixture of LTMs is employed. bf (3) We derive general formulas for magnification factors in latent trait models. Magnification factors are a useful tool to improve our understanding of the visualisation plots, since they can highlight the boundaries between data clusters. The unsupervised construction is particularly useful when high-level plots are covered with dense clusters of highly overlapping data projections, making it difficult to use the interactive mode. Such a situation often arises when visualizing large data sets. We illustrate our approach on a toy example and apply our system to three more complex real data sets.

Lithological mapping of Northwest Argentina with remote sensing data using tonal, textural and contextual features

Tonal, textural and contextual properties are used in manual photointerpretation of remotely sensed data. This study has used these three attributes to produce a lithological map of semi arid northwest Argentina by semi automatic computer classification procedures of remotely sensed data. Three different types of satellite data were investigated, these were LANDSAT MSS, TM and SIR-A imagery. Supervised classification procedures using tonal features only produced poor classification results. LANDSAT MSS produced classification accuracies in the range of 40 to 60%, while accuracies of 50 to 70% were achieved using LANDSAT TM data. The addition of SIR-A data produced increases in the classification accuracy. The increased classification accuracy of TM over the MSS is because of the better discrimination of geological materials afforded by the middle infra red bands of the TM sensor. The maximum likelihood classifier consistently produced classification accuracies 10 to 15% higher than either the minimum distance to means or decision tree classifier, this improved accuracy was obtained at the cost of greatly increased processing time. A new type of classifier the spectral shape classifier, which is computationally as fast as a minimum distance to means classifier is described. However, the results for this classifier were disappointing, being lower in most cases than the minimum distance or decision tree procedures. The classification results using only tonal features were felt to be unacceptably poor, therefore textural attributes were investigated. Texture is an important attribute used by photogeologists to discriminate lithology. In the case of TM data, texture measures were found to increase the classification accuracy by up to 15%. However, in the case of the LANDSAT MSS data the use of texture measures did not provide any significant increase in the accuracy of classification. For TM data, it was found that second order texture, especially the SGLDM based measures, produced highest classification accuracy. Contextual post processing was found to increase classification accuracy and improve the visual appearance of classified output by removing isolated misclassified pixels which tend to clutter classified images. Simple contextual features, such as mode filters were found to out perform more complex features such as gravitational filter or minimal area replacement methods. Generally the larger the size of the filter, the greater the increase in the accuracy. Production rules were used to build a knowledge based system which used tonal and textural features to identify sedimentary lithologies in each of the two test sites. The knowledge based system was able to identify six out of ten lithologies correctly.

A Bayesian modeling approach to multi-dimensional sentiment distributions prediction

Sentiment analysis has long focused on binary classification of text as either positive or negative. There has been few work on mapping sentiments or emotions into multiple dimensions. This paper studies a Bayesian modeling approach to multi-class sentiment classification and multidimensional sentiment distributions prediction. It proposes effective mechanisms to incorporate supervised information such as labeled feature constraints and document-level sentiment distributions derived from the training data into model learning. We have evaluated our approach on the datasets collected from the confession section of the Experience Project website where people share their life experiences and personal stories. Our results show that using the latent representation of the training documents derived from our approach as features to build a maximum entropy classifier outperforms other approaches on multi-class sentiment classification. In the more difficult task of multi-dimensional sentiment distributions prediction, our approach gives superior performance compared to a few competitive baselines. © 2012 ACM.

Weakly supervised joint sentiment-topic detection from text

Sentiment analysis or opinion mining aims to use automated tools to detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework called joint sentiment-topic (JST) model based on latent Dirichlet allocation (LDA), which detects sentiment and topic simultaneously from text. A reparameterized version of the JST model called Reverse-JST, obtained by reversing the sequence of sentiment and topic generation in the modeling process, is also studied. Although JST is equivalent to Reverse-JST without a hierarchical prior, extensive experiments show that when sentiment priors are added, JST performs consistently better than Reverse-JST. Besides, unlike supervised approaches to sentiment classification which often fail to produce satisfactory performance when shifting to other domains, the weakly supervised nature of JST makes it highly portable to other domains. This is verified by the experimental results on data sets from five different domains where the JST model even outperforms existing semi-supervised approaches in some of the data sets despite using no labeled documents. Moreover, the topics and topic sentiment detected by JST are indeed coherent and informative. We hypothesize that the JST model can readily meet the demand of large-scale sentiment analysis from the web in an open-ended fashion.

Self-training from labeled features for sentiment analysis

Sentiment analysis concerns about automatically identifying sentiment or opinion expressed in a given piece of text. Most prior work either use prior lexical knowledge defined as sentiment polarity of words or view the task as a text classification problem and rely on labeled corpora to train a sentiment classifier. While lexicon-based approaches do not adapt well to different domains, corpus-based approaches require expensive manual annotation effort. In this paper, we propose a novel framework where an initial classifier is learned by incorporating prior information extracted from an existing sentiment lexicon with preferences on expectations of sentiment labels of those lexicon words being expressed using generalized expectation criteria. Documents classified with high confidence are then used as pseudo-labeled examples for automatical domain-specific feature acquisition. The word-class distributions of such self-learned features are estimated from the pseudo-labeled examples and are used to train another classifier by constraining the model's predictions on unlabeled instances. Experiments on both the movie-review data and the multi-domain sentiment dataset show that our approach attains comparable or better performance than existing weakly-supervised sentiment classification methods despite using no labeled documents.

Incorporating sentiment prior knowledge for weakly supervised sentiment analysis

This article presents two novel approaches for incorporating sentiment prior knowledge into the topic model for weakly supervised sentiment analysis where sentiment labels are considered as topics. One is by modifying the Dirichlet prior for topic-word distribution (LDA-DP), the other is by augmenting the model objective function through adding terms that express preferences on expectations of sentiment labels of the lexicon words using generalized expectation criteria (LDA-GE). We conducted extensive experiments on English movie review data and multi-domain sentiment dataset as well as Chinese product reviews about mobile phones, digital cameras, MP3 players, and monitors. The results show that while both LDA-DP and LDAGE perform comparably to existing weakly supervised sentiment classification algorithms, they are much simpler and computationally efficient, rendering themmore suitable for online and real-time sentiment classification on the Web. We observed that LDA-GE is more effective than LDA-DP, suggesting that it should be preferred when considering employing the topic model for sentiment analysis. Moreover, both models are able to extract highly domain-salient polarity words from text.

Learning sentiment classification model from labeled features

We propose a novel framework where an initial classifier is learned by incorporating prior information extracted from an existing sentiment lexicon. Preferences on expectations of sentiment labels of those lexicon words are expressed using generalized expectation criteria. Documents classified with high confidence are then used as pseudo-labeled examples for automatical domain-specific feature acquisition. The word-class distributions of such self-learned features are estimated from the pseudo-labeled examples and are used to train another classifier by constraining the model's predictions on unlabeled instances. Experiments on both the movie review data and the multi-domain sentiment dataset show that our approach attains comparable or better performance than exiting weakly-supervised sentiment classification methods despite using no labeled documents.

Feature LDA:a supervised topic model for automatic detection of web API documentations from the web

Web APIs have gained increasing popularity in recent Web service technology development owing to its simplicity of technology stack and the proliferation of mashups. However, efficiently discovering Web APIs and the relevant documentations on the Web is still a challenging task even with the best resources available on the Web. In this paper we cast the problem of detecting the Web API documentations as a text classification problem of classifying a given Web page as Web API associated or not. We propose a supervised generative topic model called feature latent Dirichlet allocation (feaLDA) which offers a generic probabilistic framework for automatic detection of Web APIs. feaLDA not only captures the correspondence between data and the associated class labels, but also provides a mechanism for incorporating side information such as labelled features automatically learned from data that can effectively help improving classification performance. Extensive experiments on our Web APIs documentation dataset shows that the feaLDA model outperforms three strong supervised baselines including naive Bayes, support vector machines, and the maximum entropy model, by over 3% in classification accuracy. In addition, feaLDA also gives superior performance when compared against other existing supervised topic models.