This paper focusses on the main issues related to the development of a corpus for opinion and sentiment analysis, with a special attention to irony, and presents as a case study Senti-TUT, a project for Italian aimed at investigating sentiment and irony in social media. We present the Senti-TUT corpus, a collection of texts from Twitter annotated with sentiment polarity. We describe the dataset, the annotation, the methodologies applied and our investigations on two important features of irony: polarity reversing and emotion expressions.

The domain adaptation problem arises often in the field of sentiment classification. There are two distinct needs in domain adaptation, namely labeling adaptation and instance adaptation. Most of current research focuses on the former one, while neglects the latter one. In this work, we propose a joint approach, named feature ensemble plus sample selection (SS-FE), which takes both types of adaptation into account. A feature ensemble (FE) model is first proposed to learn a new labeling function in a feature re-weighting manner. Furthermore, a PCA-based sample selection (PCA-SS) method is proposed as an aid to FE for instance adaptation. Experimental results show that the proposed SS-FE approach could gain significant improvements, compared to individual FE and PCA-SS, due to its comprehensive consideration of both labeling adaptation and instance adaptation.

We present a supervised framework for expanding an opinion lexicon for tweets. The lexicon contains part-of-speech (POS) disambiguated entries with a three-dimensional probability distribution for positive, negative, and neutral polarities. To obtain this distribution using machine learning, we propose word-level attributes based on POS tags and information calculated from streams of emoticon-annotated tweets. Our experimental results show that our method outperforms the three-dimensional word-level polarity classification performance obtained by semantic orientation, a state-of-the-art measure for establishing world-level sentiment.

Cross-lingual sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of data in a label-scarce target language by exploiting labeled data from a label-rich language. The fundamental challenge of cross-lingual learning stems from a lack of overlap between the feature spaces of the source language data and that of the target language data. To address this challenge, previous work in the literature mainly relies on the large amount of bilingual parallel corpora to bridge the language gap. In many real applications, however, it is often the case that we have some partial parallel data but it is an expensive and time-consuming job to acquire large amount of parallel data on different languages. In this paper, we propose a novel subspace learning framework by leveraging the partial parallel data for cross-lingual sentiment classification. The proposed approach is achieved by jointly learning the document-aligned review data and un-aligned data from the source language and the target language via a non-negative matrix factorization framework. We conduct a set of experiments with cross-lingual sentiment classification tasks on multilingual Amazon product reviews. Our experimental results demonstrate the efficacy of the proposed cross-lingual approach.

Current methods of sentiment analysis for social media images include low-level visual feature based approaches [Jia et Recently text-based sentiment prediction has been al., 2012; Yang et al., 2014], mid-level visual feature based extensively studied, while image-centric sentiment approaches [Borth et al., 2013; Yuan et al., 2013] and deep analysis receives much less attention. In this paper, learning based approaches [You et al., 2015]. The vast majority we study the problem of understanding human of existing methods are supervised, relying on labeled images sentiments from large-scale social media images, to train sentiment classifiers. Unfortunately, sentiment considering both visual content and contextual information, labels are in general unavailable for social media images, and such as comments on the images, captions, it is too labor-and time-intensive to obtain labeled sets large etc. The challenge of this problem lies in enough for robust training. In order to utilize the vast amount the "semantic gap" between low-level visual features of unlabeled social media images, an unsupervised approach and higher-level image sentiments. Moreover, would be much more desirable.

Sentiment expression in microblog posts often reflects user's specific individuality due to different language habit, personal character, opinion bias and so on. Existing sentiment classification algorithms largely ignore such latent personal distinctions among different microblog users. Meanwhile, sentiment data of microblogs are sparse for individual users, making it infeasible to learn effective personalized classifier. In this paper, we propose a novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space. We alleviate the sparsity of personal texts by decomposing the posts into words which are further represented by the weighted sentiment and topic units based on a set of syntactic units of words obtained from dependency parsing results. To strengthen the representation of users, we leverage users following relation to consolidate the individuality of a user fused from other users with similar interests. Results on real-world microblog datasets confirm that our method outperforms state-of-the-art baseline algorithms with large margins.

User-item connected documents, such as customer reviews for specific items in online shopping website and user tips in location-based social networks, have become more and more prevalent recently. Inferring the topic distributions of user-item connected documents is beneficial for many applications, including document classification and summarization of users and items. While many different topic models have been proposed for modeling multiple text, most of them cannot account for the dual role of user-item connected documents (each document is related to one user and one item simultaneously) in topic distribution generation process. In this paper, we propose a novel probabilistic topic model called Prior-based Dual Additive Latent Dirichlet Allocation (PDA-LDA). It addresses the dual role of each document by associating its Dirichlet prior for topic distribution with user and item topic factors, which leads to a document-level asymmetric Dirichlet prior. In the experiments, we evaluate PDA-LDA on several real datasets and the results demonstrate that our model is effective in comparison to several other models, including held-out perplexity on modeling text and document classification application.

Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). In real applications, these user generated sentiment data can span so many different domains that it is difficult to manually label training data for all of them. Hence, this paper studies the problem of domain adaptation for sentiment classification where a systemtrained using labeled reviews from a source domain is deployed to classify sentimentsof reviews in a different target domain. In this paper, we propose to link heterogeneous input features with pivots via joint non-negative matrix factorization. This is achieved by learning the domain-specific information from different domains into unified topics, with the help of pivots across all domains. We conduct experiments on a benchmark composed of reviews of 4 types of Amazon products. Experimental results show that our proposed approach significantly outperforms the baseline method, and achieves an accuracy which is competitive with the state-of-the-art methods for sentiment classification adaptation.

Topic modeling has been widely used in text mining. Previous topic models such as Latent Dirichlet Allocation (LDA) are successful in learning hidden topics but they do not take into account metadata of documents. To tackle this problem, many augmented topic models have been proposed to jointly model text and metadata. But most existing models handle only categorical and numerical types of metadata. We identify another type of metadata that can be more natural to obtain in some scenarios. These are relative similarities among documents. In this paper, we propose a general model that links LDA with constraints derived from document relative similarities. Specifically, in our model, the constraints act as a regularizer of the log likelihood of LDA. We fit the proposed model using Gibbs-EM. Experiments with two real world datasets show that our model is able to learn meaningful topics. The results also show that our model outperforms the baselines in terms of topic coherence and a document classification task.

Target-dependent sentiment analysis on Twitter has attracted increasing research attention. Most previous work relies on syntax, such as automatic parse trees, which are subject to noise for informal text such as tweets. In this paper, we show that competitive results can be achieved without the use of syntax, by extracting a rich set of automatic features. In particular, we split a tweet into a left context and a right context according to a given target, using distributed word representations and neural pooling functions to extract features. Both sentiment-driven and standard embeddings are used, and a rich set of neural pooling functions are explored. Sentiment lexicons are used as an additional source of information for feature extraction. In standard evaluation, the conceptually simple method gives a 4.8% absolute improvement over the state-of-the-art on three-way targeted sentiment classification, achieving the best reported results for this task.