Abstract | Furthermore, using feature augmentation and selection according to the information gain criteria for cross-domain sentiment classification , our proposed approach performs either better or comparably compared to previous approaches. |
Introduction | Given a piece of text, sentiment classification aims to determine whether the semantic orientation of the text is positive, negative or neutral. |
Introduction | With prior polarity words extracted from both the MPQA subjectivity lexicon1 and the appraisal lexiconz, the J ST model achieves a sentiment classification accuracy of 74% on the movie review data3 and 71% on the multi-domain sentiment dataset4. |
Introduction | The fact that the J ST model does not required any labeled documents for training makes it desirable for domain adaptation in sentiment classification . |
Joint Sentiment-Topic (J ST) Model | These observations motivate us to explore polarity-bearing topics extracted by JST for cross-domain sentiment classification since grouping words from different domains but bearing similar sentiment has the effect of overcoming the data distribution difference of two domains. |
Joint Sentiment-Topic (J ST) Model | Output: A sentiment classifier for the target domain Pt 1: Merge D8 and Pt with document labels discarded, D: {(51331 3 ng Nfimfwl 3 ng Nt} |
Joint Sentiment-Topic (J ST) Model | Input: The target domain data, 13’5 = E X : 1 g n g N75, N75 > N5}, document sentiment classification threshold 7' Output: A labeled document pool 13 1: Train a J ST model parameterized by A on D75 2: for each document 533,5, 6 D75 do 3: Infer its sentiment class label from JST as ln = arg max, P(l|:cf,; A) |
Related Work | proposed structural correspondence learning (SCL) for domain adaptation in sentiment classification . |
Abstract | This paper presents a method for multimodal sentiment classification , which can identify the sentiment expressed in utterance-level visual datastreams. |
Conclusions | In this paper, we presented a multimodal approach for utterance-level sentiment classification . |
Conclusions | Table 4: Video-level sentiment classification with linguistic, acoustic, and visual features. |
Discussion | The experimental results show that sentiment classification can be effectively performed on multimodal datastreams. |
Discussion | Other informative features for sentiment classification are the voice probability, representing the energy in speech, the combined visual features that represent an angry face, and two of the cepstral coefficients. |
Discussion | To understand the role played by the size of the video-segments considered in the sentiment classification experiments, as well as the potential effect of a speaker-independence assumption, we also run a set of experiments where we use full videos for the classification. |
Experiments and Results | We run our sentiment classification experiments on the MOUD dataset introduced earlier. |
Experiments and Results | Table 2: Utterance-level sentiment classification with linguistic, acoustic, and visual features. |
Experiments and Results | Table 2 shows the results of the utterance-level sentiment classification experiments. |
Introduction | Our experiments and results on multimodal sentiment classification are presented in Section 5, with a detailed discussion and analysis in Section 6. |
Multimodal Sentiment Analysis | These simple weighted unigram features have been successfully used in the past to build sentiment classifiers on text, and in conjunction with Support Vector Machines (SVM) have been shown to lead to state-of-the-art performance (Maas et al., 2011). |
Abstract | Such a disproportion arouse interest in cross-lingual sentiment classification, which aims to conduct sentiment classification in the target language (e.g. |
Introduction | Sentiment classification , the task of determining the sentiment orientation (positive, negative or neutral) of text, has been the most extensively studied task in sentiment analysis. |
Introduction | lel for Sentiment Classification |
Introduction | already a large amount of work on sentiment classification of text in various genres and in many languages. |
Abstract | We evaluate our method on two tasks: cross-domain part-of-speech tagging and cross-domain sentiment classification . |
Distribution Prediction | Bigram features capture negations more accurately than unigrams, and have been found to be useful for sentiment classification tasks. |
Distribution Prediction | As we go on to show in Section 6, this enables us to use the same distribution prediction method for both POS tagging and sentiment classification . |
Domain Adaptation | We consider two DA tasks: (a) cross-domain POS tagging (Section 4.1), and (b) cross-domain sentiment classification (Section 4.2). |
Domain Adaptation | 4.2 Cross-Domain Sentiment Classification |
Domain Adaptation | Unlike in POS tagging, where we must individually tag each word in a target domain test sentence, in sentiment classification we must classify the sentiment for the entire review. |
Introduction | For example, unsupervised cross-domain sentiment classification (Blitzer et al., 2007; Aue and Gamon, 2005) involves using sentiment-labeled user reviews from the source domain, and unlabeled reviews from both the source and the target domains to learn a sentiment classifier for the target domain. |
Introduction | Domain adaptation (DA) of sentiment classification becomes extremely challenging when the distributions of words in the source and the target domains are very different, because the features learnt from the source domain labeled reviews might not appear in the target domain reviews that must be classified. |
Introduction | 0 Using the learnt distribution prediction model, we propose a method to learn a cross-domain sentiment classifier . |
Related Work | Prior knowledge of the sentiment of words, such as sentiment lexicons, has been incorporated into cross-domain sentiment classification . |
Related Work | Although incorporation of prior sentiment knowledge is a promising technique to improve accuracy in cross-domain sentiment classification , it is complementary to our task of distribution prediction across domains. |
A Joint Model with Unlabeled Parallel Text | Given the input data D1, D2 and U, our task is to jointly learn two monolingual sentiment classifiers — one for L1 and one for L2. |
Abstract | We present a novel approach for joint bilingual sentiment classification at the sentence level that augments available labeled data in each language with unlabeled parallel data. |
Abstract | We rely on the intuition that the sentiment labels for parallel sentences should be similar and present a model that jointly learns improved monolingual sentiment classifiers for each language. |
Introduction | Not surprisingly, most methods for sentiment classification are supervised learning techniques, which require training data annotated with the appropriate sentiment labels (e. g. document-level or sentence-level positive vs. negative polarity). |
Introduction | In addition, there is still much room for improvement in existing monolingual (including English) sentiment classifiers , especially at the sentence level (Pang and Lee, 2008). |
Introduction | In contrast to previous work, we (1) assume that some amount of sentiment-labeled data is available for the language pair under study, and (2) investigate methods to simultaneously improve sentiment classification for both languages. |
Related Work | Prettenhofer and Stein (2010) investigate cross-lingual sentiment classification from the perspective of domain adaptation based on structural correspondence learning (Blitzer et al., 2006). |
Related Work | Approaches that do not explicitly involve resource adaptation include Wan (2009), which uses co-training (Blum and Mitchell, 1998) with English vs. Chinese features comprising the two independent “views” to exploit unlabeled Chinese data and a labeled English corpus and thereby improves Chinese sentiment classification . |
Related Work | Unlike the methods described above, we focus on simultaneously improving the performance of sentiment classification in a pair of languages by developing a model that relies on sentiment-labeled data in each language as well as unlabeled parallel text for the language pair. |
Abstract | In this paper, we focus on target-dependent Twitter sentiment classification ; namely, given a query, we classify the sentiments of the tweets as positive, negative or neutral according to whether they conuun posfljve, negafive or nqual senfi-ments about that query. |
Abstract | However, because tweets are usually short and more ambiguous, sometimes it is not enough to consider only the current tweet for sentiment classification . |
Abstract | In this paper, we propose to improve target-dependent Twitter sentiment classification by 1) incorporating target-dependent features; and 2) taking related tweets into consideration. |
Introduction | 3r Sentiment Classification |
Introduction | The problem needing to be addressed can be formally named as Target-dependent Sentiment Classification of Tweets; namely, given a query, classifying the sentiments of the tweets as positive, negative or neutral according to whether they contain positive, negative or neutral sentiments about that query. |
Introduction | The state-of-the-art approaches for solving this problem, such as (Go et al., 20095; Barbosa and Feng, 2010), basically follow (Pang et al., 2002), who utilize machine learning based classifiers for the sentiment classification of texts. |
Abstract | We describe a sentiment classification method that is applicable when we do not have any labeled data for a target domain but have some labeled data for multiple other domains, designated as the source domains. |
Abstract | Unlike previous cross-domain sentiment classification methods, our method can efficiently learn from multiple source domains. |
Abstract | Our method significantly outperforms numerous baselines and returns results that are better than or comparable to previous cross-domain sentiment classification methods on a benchmark dataset containing Amazon user reviews for different types of products. |
Introduction | Automatic document level sentiment classification (Pang et al., 2002; Tumey, 2002) is the task of classifying a given review with respect to the sentiment expressed by the author of the review. |
Introduction | For example, a sentiment classifier might classify a user review about a movie as positive or negative depending on the sentiment |
Introduction | Sentiment classification has been applied in numerous tasks such as opinion mining (Pang and Lee, 2008), opinion summarization (Lu et al., 2009), contextual advertising (Fan and Chang, 2010), and market analysis (Hu and Liu, 2004). |
Abstract | In this paper, we adopt two views, personal and impersonal views, and systematically employ them in both supervised and semi-supervised sentiment classification . |
Abstract | On this basis, an ensemble method and a co—training algorithm are explored to employ the two views in supervised and semi-supervised sentiment classification respectively. |
Introduction | As a special task of text classification, sentiment classification aims to classify a text according to the expressed sentimental polarities of opinions such as ‘thumb up’ or ‘thumb down’ on the movies (Pang et al., 2002). |
Introduction | In general, the objective of sentiment classification can be represented as a kind of binary relation R, defined as an ordered triple (X, Y, G), where X is an object set including different kinds of people (e. g. writers, reviewers, or users), Y is another object set including the target objects (e.g. |
Introduction | The concerned relation in sentiment classification is X ’s evaluation on Y, such as ‘thumb up’, ‘thumb down’, ‘favorable’, |
Abstract | The lack of Chinese sentiment corpora limits the research progress on Chinese sentiment classification . |
Abstract | This paper focuses on the problem of cross-lingual sentiment classification, which leverages an available English corpus for Chinese sentiment classification by using the English corpus as training data. |
Introduction | Sentiment classification is the task of identifying the sentiment polarity of a given text. |
Introduction | In recent years, sentiment classification has drawn much attention in the NLP field and it has many useful applications, such as opinion mining and summarization (Liu et al., 2005; Ku et al., 2006; Titov and McDonald, 2008). |
Introduction | To date, a variety of corpus-based methods have been developed for sentiment classification . |
Abstract | We present a method that learns word embedding for Twitter sentiment classification in this paper. |
Abstract | Experiments on applying SSWE to a benchmark Twitter sentiment classification dataset in SemEval 2013 show that (1) the SSWE feature performs comparably with handcrafted features in the top-performed system; (2) the performance is further improved by concatenating SSWE with existing feature set. |
Introduction | Twitter sentiment classification has attracted increasing research interest in recent years (J iang et al., 2011; Hu et al., 2013). |
Introduction | (2013) build the top-performed system in the Twitter sentiment classification track of SemEval 2013 (Nakov et al., 2013), using diverse sentiment lexicons and a variety of handcrafted features. |
Introduction | For the task of sentiment classification , an effective feature leam-ing method is to compose the representation of a sentence (or document) from the representations of the words or phrases it contains (Socher et al., 2013b; Yessenalina and Cardie, 2011). |
Related Work | In this section, we present a brief review of the related work from two perspectives, Twitter sentiment classification and learning continuous representations for sentiment classification . |
Related Work | 2.1 Twitter Sentiment Classification |
Approach | We formulate the sentence-level sentiment classification task as a sequence labeling problem. |
Approach | In this work, we apply PR in the context of CRFs for sentence-level sentiment classification . |
Experiments | We experimented with two product review datasets for sentence-level sentiment classification : the Customer Review (CR) data (Hu and Liu, 2004)6 which contains 638 reviews of 14 products such as cameras and cell phones, and the Multi-domain Amazon (MD) data from the test set of Tackstro'm and McDonald (201 la) which contains 294 reivews from 5 different domains. |
Introduction | In this paper, we focus on the task of sentence-level sentiment classification in online reviews. |
Introduction | Semi-supervised techniques have been proposed for sentence-level sentiment classification (Tackstro'm and McDonald, 2011a; Qu et al., 2012). |
Introduction | In this paper, we propose a sentence-level sentiment classification method that can (1) incorporate rich discourse information at both local and global levels; (2) encode discourse knowledge as soft constraints during learning; (3) make use of unlabeled data to enhance learning. |
Related Work | In this paper, we focus on the study of sentence-level sentiment classification . |
Related Work | Compared to the existing work on semi-supervised learning for sentence-level sentiment classification (Tackstro'm and McDonald, 2011a; Tackstrom and McDonald, 2011b; Qu et al., 2012), our work does not rely on a large amount of coarse-grained (document-level) labeled data, instead, distant supervision mainly comes from linguistically-motivated constraints. |
Abstract | Our sentiment classification model achieves approximately 1% greater accuracy than a state-of—the-art approach based on elementary discourse units. |
Experiments | We train 15 sentiment classification models using all basic features and their combinations. |
Experiments | To this end, we train and compare sentiment classification models using three configurations. |
Experiments | This is important because to compare only the lexicons’ impact on sentiment classification , we need to avoid the effect of other factors, such as syntax, transition cues, and so on. |
Framework | Knowledge from this initial training set is not sufficient to build an accurate sentiment classification model or to generate a domain-specific sentiment lexicon. |
Framework | for training a CRF-based sentiment classification model. |
Introduction | In respect to sentiment classification , Pang et al. |
Introduction | (1) Instead of using sentences, ReNew uses segments as the basic units for sentiment classification . |
Introduction | Additionally, our sentiment classification model achieves approximately 1% greater accuracy than a state-of-the-art approach based on elementary discourse units (Lazaridou et al., 2013). |
Introduction | However, most of them focused on coarse-grained document-level sentiment classification , which is different from our fine-grained word-level extraction. |
Introduction | 7 Application: Sentiment Classification |
Introduction | To further verify the usefulness of the lexicons extracted by the RAP method, we apply the extracted sentiment lexicon for sentiment classification . |
Abstract | We conduct experiments in the field of cross-language sentiment classification , employing English as source language, and German, French, and Japanese as target languages. |
Conclusion | The analysis covers performance and robustness issues in the context of cross-language sentiment classification with English as source language and German, French, and Japanese as target languages. |
Cross-Language Structural Correspondence Learning | Considering our sentiment classification example, the word pair {excellent3, exzellentT} satisfies both conditions: (1) the words are strong indicators of positive sentiment, |
Experiments | We evaluate CL—SCL for the task of cross-language sentiment classification using English as source language and German, French, and Japanese as target languages. |
Experiments | We compiled a new dataset for cross-language sentiment classification by crawling product reviews from Amazon. |
Experiments | Statistical machine translation technology offers a straightforward solution to the problem of cross-language text classification and has been used in a number of cross-language sentiment classification studies (Hiroshi et al., 2004; Bautin et al., 2008; Wan, 2009). |
Introduction | 7 may be a spam filtering task, a topic categorization task, or a sentiment classification task. |
Introduction | In this connection we compile extensive corpora in the languages English, German, French, and Japanese, and for different sentiment classification tasks. |
Introduction | Section 5 presents experimental results in the context of cross-language sentiment classification . |
Abstract | Expensive feature engineering based on WordNet senses has been shown to be useful for document level sentiment classification . |
Clustering for Cross Lingual Sentiment Analysis | The language whose annotated data is used for training is called the source language (8), while the language whose documents are to be sentiment classified is referred to as the target language (T). |
Clustering for Cross Lingual Sentiment Analysis | Algorithm 1 Projection based on sense Input: Polarity labeled data in source language (S) and data in target language (T) to be labeled Output: Classified documents 1: Sense mark the polarity labeled data from S 2: Project the sense marked corpora from S to T using a Multidict 3: Model the sentiment classifier using the data obtained in step-2 4: Sense mark the unlabelled data from T 5: Test the sentiment classifier on data obtained in step-4 using model obtained in step-3 |
Clustering for Sentiment Analysis | (2011) showed that WordNet synsets can act as good features for document level sentiment classification . |
Clustering for Sentiment Analysis | In this study, synset identifiers are extracted from manually/automatically sense annotated corpora and used as features for creating sentiment classifiers . |
Clustering for Sentiment Analysis | of sentiment classification , cluster identifiers |
Discussions | Whereas, sentiment classifier using sense (PS) or direct cluster linking (DCL) is not very effective. |
Experimental Setup | SVM was used since it is known to perform well for sentiment classification (Pang et al., 2002). |
Introduction | Word clustering is a powerful mechanism to “transfer” a sentiment classifier from one language to another. |
Experiment | Our experiments consist of an opinion retrieval task and a sentiment classification task. |
Experiment | (2002) to test various ML—based methods for sentiment classification . |
Experiment | We present the sentiment classification performances in Table 3. |
Related Work | (2002) presents empirical results indicating that using term presence over term frequency is more effective in a data-driven sentiment classification task. |
Term Weighting and Sentiment Analysis | In this section, we describe the characteristics of terms that are useful in sentiment analysis, and present our sentiment analysis model as part of an opinion retrieval system and an ML sentiment classifier . |
Abstract | We propose Adaptive Recursive Neural Network (AdaRNN) for target-dependent Twitter sentiment classification . |
Conclusion | We propose Adaptive Recursive Neural Network (AdaRNN) for the target-dependent Twitter sentiment classification . |
Experiments | To the best of our knowledge, this is the largest target-dependent Twitter sentiment classification dataset which is annotated manually. |
Experiments | Table 1: Evaluation results on target-dependent Twitter sentiment classification dataset. |
Introduction | For target-dependent sentiment classification , the manual evaluation of Jiang et al. |
Introduction | The neural models use distributed representation (Hinton, 1986; Rumelhart et al., 1986; Bengio et al., 2003) to automatically learn features for target-dependent sentiment classification . |
Abstract | We show that this constraint is effective on the sentiment classification task (Fang et al., 2002), resulting in scores similar to the ones obtained by the structural correspondence methods (Blitzer et al., 2007) without the need to engineer auxiliary tasks. |
Discussion and Conclusions | Our approach results in competitive domain-adaptation performance on the sentiment classification task, rivalling that of the state-of-the-art SCL method (Blitzer et al., 2007). |
Empirical Evaluation | In this section we empirically evaluate our approach on the sentiment classification task. |
Empirical Evaluation | On the sentiment classification task in order to construct them two steps need to be performed: (1) a set of words correlated with the sentiment label is selected, and, then (2) prediction of each such word is regarded a distinct auxiliary problem. |
Introduction | We evaluate our approach on adapting sentiment classifiers on 4 domains: books, DVDs, electronics and kitchen appliances (Blitzer et al., 2007). |
Conclusion | Experiments also demonstrate that inclusion of new sentiment words benefits sentiment classification definitely. |
Experiment | In this section, we will conduct the following experiments: first, we will compare our method to several baselines, and perform parameter tuning with extensive experiments; second, we will classify polarity of new sentiment words using two methods; third, we will demonstrate how new sentiment words will benefit sentiment classification . |
Experiment | 4.6 Application of New Sentiment Words to Sentiment Classification |
Experiment | In this section, we justify whether inclusion of new sentiment word would benefit sentiment classification . |
Introduction | ° We investigate the problem of polarity prediction of new sentiment word and demonstrate that inclusion of new sentiment word benefits sentiment classification tasks. |
Abstract | To address this problem, we propose a semi-supervised approach to sentiment classification where we first mine the unambiguous reviews using spectral techniques and then exploit them to classify the ambiguous reviews via a novel combination of active learning, transductive learning, and ensemble learning. |
Conclusions | First, none of the steps in our approach is designed specifically for sentiment classification . |
Evaluation | For evaluation, we use five sentiment classification datasets, including the widely-used movie review dataset [MOV] (Pang et al., 2002) as well as four datasets that contain reviews of four different types of product from Amazon [books (BOO), DVDs (DVD), electronics (ELE), and kitchen appliances (KIT)] (Blitzer et al., 2007). |
Introduction | perimental results on five sentiment classification datasets demonstrate that our system can generate high-quality labeled data from unambiguous reviews, which, together with a small number of manually labeled reviews selected by the active learner, can be used to effectively classify ambiguous reviews in a discriminative fashion. |
Introduction | Section 2 gives an overview of spectral clustering, which will facilitate the presentation of our approach to unsupervised sentiment classification in Section 3. |
Abstract | We show improvement on the task of sentiment classification with respect to several baselines, and observe that the approach is most useful when the training set is sufficiently small. |
Future Work | While “semantic smoothing” obtained from introducing an external embedding helps to improve performance in the sentiment classification task, the method does not help to re-embed words that do not appear in the training set to begin with. |
Related Work | The most relevant to our contribution is the work by Maas et.al (2011), where word vectors are learned specifically for sentiment classification . |
Results and Discussion | Source embeddings: We find C&W embeddings to perform best for the task of sentiment classification . |
Background and Related Work | Research has been made on sentiment classification in document-level (Turney et al., 2002, Pang et al., 2002, Seki et al. |
Background and Related Work | The discourse of contentious issues in news articles show different characteristics from that studied in the sentiment classification tasks. |
Background and Related Work | They assume a debate frame, which is similar to the frame of the sentiment classification task, i.e., for vs. against the debate topic. |
Introduction | Research on sentiment classification and debate stance recognition takes a topic-oriented view, and attempts to perform classification under the ‘positive vs. negative’ or ‘for vs. against’ frame for the given topic, e. g., positive vs. negative about iPhone. |
Experiments | Sentiment classification . |
Experiments | (a) Sentiment classification |
Experiments | (a) Sentiment classification |
Representations and models | This would strongly bias the FVEC sentiment classifier to assign a positive label to the comment. |
Experiments | To combat this problem we first train the sentiment classifiers by assuming that pygm is equal for all the local topics, which effectively ignores the topic model. |
Introduction | The second problem is sentiment classification . |
Introduction | Sentiment classification is a well studied problem (Wiebe, 2000; Pang et a1., 2002; Tumey, 2002) and in many domains users explicitly |
The Model | Therefore, the use of the aspect sentiment classifiers based only on the words assigned to the corresponding topics is problematic. |
Problem Definition | 4.1.3 Sentiment Classification Data |
Problem Definition | In the domain of Sentiment Classification , we tested on the Amazon dataset from (Blitzer et al., 2007). |
Problem Definition | In the Amazon Sentiment Classification data set, the task is to determine whether a review is positive or negative based solely on the reviewer’s submitted text. |
Domain Adaptation in Sentiment Research | Most text-level sentiment classifiers use standard machine learning techniques to learn and select features from labeled corpora. |
Domain Adaptation in Sentiment Research | (2007) applied structural correspondence learning (Drezde et al., 2007) to the task of domain adaptation for sentiment classification of product reviews. |
Factors Affecting System Performance | To our knowledge, the only work that describes the application of statistical classifiers (SVM) to sentence-level sentiment classification is (Gamon and Aue, 2005)1. |
Abstract | We evaluate the model using small, widely used sentiment and subjectivity corpora and find it outperforms several previously introduced methods for sentiment classification . |
Experiments | Of course, this is only an impressionistic analysis of a few cases, but it is helpful in understanding why the sentiment-enriched model proves superior at the sentiment classification results we report next. |
Related work | Martineau and Finin present evidence that this weighting helps with sentiment classification , and Paltoglou and Thelwall (2010) systematically explore a number of weighting schemes in the context of sentiment analysis. |
Abstract | Sentiment classification refers to the task of automatically identifying whether a given piece of text expresses positive or negative opinion towards a subject at hand. |
Experiments | In particular, the use of SVMs in (Pang et al., 2002) initially sparked interest in using machine learning methods for sentiment classification . |
Related Work | A two-tier scheme (Pang and Lee, 2004) where sentences are first classified as subjective versus objective, and then applying the sentiment classifier on only the subjective sentences further improves performance. |