Document Sentiment Classification Research Articles

Sequence encoding incorporated CNN model for Email document sentiment classification

Document sentiment classification is an area of study that has been developed for decades. However, sentiment classification of Email data is rather a specialized field that has not yet been thoroughly studied. Compared to typical social media and review data, Email data has characteristics of length variance, duplication caused by reply and forward messages, and implicitness in sentiment indicators. Due to these characteristics, existing techniques are incapable of fully capturing the complex syntactic and relational structure among words and phrases in Email documents.In this study, we introduce a dependency graph-based position encoding technique enhanced with weighted sentiment features, and incorporate it into the feature representation process. We combine encoded sentiment sequence features with traditional word embedding features as input for a revised deep CNN model for Email sentiment classification. Experiments are conducted on three sets of real Email data with adequate label conversion processes. Empirical results indicate that our proposed SSE-CNN model obtained the highest accuracy rate of 88.6%, 74.3% and 82.1% for three experimental Email datasets over other comparative state-of-the-art algorithms. Furthermore, our performance evaluations on the preprocessing and sentiment sequence encoding justify the effectiveness of Email preprocessing and sentiment sequence encoding with dependency-graph based position and SWN features on the improvement of Email document sentiment classification.

Leveraging multiple features for document sentiment classification

Sentiment classification is an important research task in Natural Language Processing. To fulfill this type of classification, previous works have focused on leveraging task-specific features. However, they only notice part of the related features. Also, state-of-the-art methods based on neural networks often ignore traditional features. This paper proposes a novel text sentiment classification method that learns the representation of texts by hierarchically incorporating multiple features. More specifically, we design different representations for sentiment words according to the polarity of labeled texts and whether negation exists; we distinguish words with different part-of-speech tags; emoticons, if there are, are to optimize the word vectors obtained in the previous step; apart from word embeddings, character embeddings are also trained. We use a deep neural network to get a sentence-level representation from both word and character sequence. For documents with at least two sentences, we use a hierarchical structure and design a rule to give more weight to import sentences empirically to get a document-level representation. Experimental results on open datasets demonstrate that our method could effectively improve the sentiment classification performance compared with the basic models and state-of-the-art methods.

EnSWF: effective features extraction and selection in conjunction with ensemble learning methods for document sentiment classification

With the rise of web 2.0, a huge amount of unstructured data has been generated on regular basis in the form of comments, opinions, etc. This unstructured data contains useful information and can play a significant role in business decision making. In this context, sentiment analysis (SA) is an active research area and has recently attracted the attention of the research community. The aim of SA is to classify the user-generated content into positive and negative class. State-of-the-art techniques for sentiment classification relies on the traditional bag-of-words approaches. Such approaches can be advantageous in terms of simplicity but completely ignore the semantics aspects, the order between words, and also leads to the curse of dimensionality. Researchers have also proposed semantic-based SA techniques in conjunction with word-order employing high order n-grams, part-of-speech (POS) patterns, and dependency relation features. But can every word or phrase of high order n-grams, POS patterns or dependency relation features represent sentiment clue? If incorporated, then what about the dimensionality? In order to tackle and investigate such issues, in this paper, we propose a novel POS and n-gram based ensemble method for SA while considering semantics, sentiment clue, and order between words called EnSWF which is a four phase process. Our main contributions are four-fold (a) Appropriate Feature Extraction: we investigate and validate extracting various appropriate features for sentiment classification. (b) Dimensionality Reduction: We decrease the dimensionality of feature space by selecting the subset of most meaningful and effective features. (c) Ensemble Model: We propose an ensemble learning method for both filter based features selection and classification using simple majority voting technique. (d) Practicality: we authenticate our claim while applying our model on benchmark datasets. We also show that EnSWF out-perform existing techniques in terms of classification accuracy and reduce high dimensional feature space.

Bootstrap Domain-Specific Sentiment Classifiers from Unlabeled Corpora

There is often the need to perform sentiment classification in a particular domain where no labeled document is available. Although we could make use of a general-purpose off-the-shelf sentiment classifier or a pre-built one for a different domain, the effectiveness would be inferior. In this paper, we explore the possibility of building domain-specific sentiment classifiers with unlabeled documents only. Our investigation indicates that in the word embeddings learned from the unlabeled corpus of a given domain, the distributed word representations (vectors) for opposite sentiments form distinct clusters, though those clusters are not transferable across domains. Exploiting such a clustering structure, we are able to utilize machine learning algorithms to induce a quality domain-specific sentiment lexicon from just a few typical sentiment words (“seeds”). An important finding is that simple linear model based supervised learning algorithms (such as linear SVM) can actually work better than more sophisticated semi-supervised/transductive learning algorithms which represent the state-of-the-art technique for sentiment lexicon induction. The induced lexicon could be applied directly in a lexicon-based method for sentiment classification, but a higher performance could be achieved through a two-phase bootstrapping method which uses the induced lexicon to assign positive/negative sentiment scores to unlabeled documents first, a nd t hen u ses those documents found to have clear sentiment signals as pseudo-labeled examples to train a document sentiment classifier v ia supervised learning algorithms (such as LSTM). On several benchmark datasets for document sentiment classification, our end-to-end pipelined approach which is overall unsupervised (except for a tiny set of seed words) outperforms existing unsupervised approaches and achieves an accuracy comparable to that of fully supervised approaches.

Attention-based Hierarchical LSTM Model for Document Sentiment Classification

Document sentiment classification is a fundamental task in data mining, contains extensive underlying commercial value. With the development of deep learning, we can extract features in an automatic way, instead of design it by oneself. Which can help us use semantic information to classify the document in a better way. Base that, in this paper, we present a hierarchical network structure according to the structure in real document. Based on LSTM to encode semantic information; then combine with attention mechanism to improve the accuracy of classification. And last, conduct experiment on two dataset, analyse the accuracy result of different model, and study some tricks in parameter selection.

Effect Research of Aspects Extraction for Chinese Hotel Reviews Based on Machine Learning Method

With the development of Web, there are more and more online reviews. These reviews have become the important information for people. Therefore, automatic analysis of online reviews has become the active research area in natural language processing and management sciences. Apart from the researches about document sentiment classification and sentence sentiment classification, there are an increasing number researches about aspect-based sentiment analysis. This paper tries to use machine learning to extract aspect from Chinese hotel reviews. Through a lot of experiments, we find that machine learning methods are suitable for the aspect extraction of Chinese reviews. This paper adopts different dimensions of features, feature representation methods and classifiers to analyze the integral effect of aspect extraction. The experiment result shows that ME is the best classifiers and presence is most suitable feature representation method for aspect extraction.

A Survey on Sentiment Analysis

The explosive growth of the textual information on the web in the past few decades has brought radical change in human life. In the web, people share their opinions and views (sentiments) in many forms about products or services they are aware of. This creates a large collection of opinions and views in the form of texts, which needs to be analysed to know the efficacy of the product or service. Opinions are usually subjective expressions that describe person's sentiment, feelings towards the object or service. The sentiment can be positive or negative. This survey is a summary of the work on sentiment analysis, covering the new challenges which appear in sentiment analysis as compared to traditional fact based analysis. Currently there are four research challenges for sentiment analysis. Those are subjectivity classification, word sentiment classification, document sentiment classification and opinion extraction. This survey discusses related issues of sentiment analysis and main approaches to those problems.

Sentiment classification: a lexical similarity based approach for extracting subjectivity in documents

With the growth of social media, document sentiment classification has become an active area of research in this decade. It can be viewed as a special case of topical classification applied only to subjective portions of a document (sources of sentiment). Hence, the key task in document sentiment classification is extracting subjectivity. Existing approaches to extract subjectivity rely heavily on linguistic resources such as sentiment lexicons and complex supervised patterns based on part-of-speech (POS) information. This makes the task of subjective feature extraction complex and resource dependent. In this work, we try to minimize the dependency on linguistic resources in sentiment classification. We propose a simple and statistical methodology called review summary (RSUMM) and use it in combination with well-known feature selection methods to extract subjectivity. Our experimental results on a movie review dataset prove the effectiveness of the proposed methodology.

Document sentiment classification by exploring description model of topical terms

Sentiment classification is used to identify whether the opinion expressed in a document is positive or negative. In this paper, we present an approach to do documentary-level sentiment classification by modeling description of topical terms. The motivation of this work stems from the observation that the global document classification will benefit greatly by examining the way of a topical term to give opinion in its local sentence context. Two sentence-level sentiment description models, namely positive and negative Topical Term Description Models, are constructed for each topical term. When analyzing a document, the Topical Term Description Models generate divergence to support the classification of its sentiment at the sentence-level which in turn can be used to decide the whole document classification collectively. The results of the experiments prove that our proposed method is effective. It is also shown that our results are comparable to the state-of-art results on a publicly available movie review corpus and a Chinese digital product review corpus. This is quite encouraging to us and motivates us to have further investigation on the development of a more effective topical term related description model in the future.

A survey on sentiment detection of reviews

The sentiment detection of texts has been witnessed a booming interest in recent years, due to the increased availability of online reviews in digital form and the ensuing need to organize them. Till to now, there are mainly four different problems predominating in this research community, namely, subjectivity classification, word sentiment classification, document sentiment classification and opinion extraction. In fact, there are inherent relations between them. Subjectivity classification can prevent the sentiment classifier from considering irrelevant or even potentially misleading text. Document sentiment classification and opinion extraction have often involved word sentiment classification techniques. This survey discusses related issues and main approaches to these problems.