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.

The daily volume of Tweets in Twitter is around 500 million, and the impact of this data on applications ranging from public safety, opinion mining, news broadcast, etc., is increasing day by day. Analyzing large volumes of Tweets for various applications would require techniques that scale well with the number of Tweets. In this work we come up with a theoretical formulation for sampling Twitter data. We introduce novel statistical metrics to quantify the statistical representativeness of the Tweet sample, and derive sufficient conditions on the number of samples needed for obtaining highly representative Tweet samples. These new statistical metrics quantify the representativeness or goodness of the sample in terms of frequent keyword identification and in terms of restoring public sentiments associated with these keywords.

The increasing use of social networks has made opinion mining an important field in the area of Natural Language Processing. The analysis of texts from the reader perspective tends to generate multi-label data since one can interpret the text using different contexts. In this paper, a new method for multi-label classification is proposed to identify reactions or emotions in texts. The new method uses data correlation to improve the class ensemble process used to create the classifiers. In addition to the new method, a new corpus of news written in Brazilian Portuguese labeled with user reactions is presented. Experiments performed with the new corpus and with two existing corpora have demonstrated that the proposed method generates statistically superior or equivalent results, requiring fewer classifiers or classes than traditional problem transformation methods.

In this study, we present an approach and a dataset for aspect-based sentiment analysis, showing how we extract and classify aspect phrases. The research field of aspect-based sentiment analysis aims at finding opinions expressed for individual characteristics of products or services in natural language texts. In the literature, reviews for common products or services such as smartphones or restaurants were mostly investigated. We describe our newly annotated dataset of German physician reviews, which presents a sensitive and linguistically complex domain, taking care to describe the annotation process and the functionality of our neural network approach. Finally, we introduce a model that can extract and classify aspect phrases in one step while obtaining an F1 score of 80%.

We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered. We show on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters. However, a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs. Our shallow word model further establishes new state-of-the-art performances on two datasets: Yelp Binary (95.9%) and Yelp Full (64.9%).

Information Extraction (IE) is the technique for transforming unstructured textual data into structured representation that can be understood by machines. The exponential growth of the Web generates an exceptional quantity of data for which automatic knowledge capture is essential. This work describes the methodology for Web scale Information Extraction adopted by the LODIE project (Linked Open Data Information Extraction). LODIE aims to develop Information Extraction techniques able to (i) scale at web level and (ii) adapt to user information need. The core idea behind LODIE is the usage of Linked Open Data, a very large-scale information resource, as a ground-breaking solution for IE, which provides invaluable annotated data on a growing number of domains.

Sentiment analysis became a hot topic, specially with the amount of opinions available in social media data. With the increasing interest in this theme, several methods have been proposed in the literature. Recent efforts have showed that there is no single method that always achieves the best prediction performance for different datasets. Additionally, novel methods have not being extensively compared with other methods and across different datasets, specially methods that are not designed to the English language. Consequently, researchers tend to accept any popular method as a valid methodology to measure sentiments, a practice that is usual in science. In this context, we propose iFeel 2.0, an online web system that implements 19 sentence-level sentiment analysis methods and allows users to easily label a dataset with all of them.

The tracking of citizens' reactions in social media during crises has attracted an increasing level of interest in the research community. In particular, sentiment analysis over social media posts can be regarded as a particularly useful tool, enabling civil protection and law enforcement agencies to more effectively respond during this type of situation. Prior work on sentiment analysis in social media during crises has applied well-known techniques for overall sentiment detection in posts. However, we argue that sentiment analysis of the overall post might not always be suitable, as it may miss the presence of more targeted sentiments, e.g. about the people and organizations involved (which we refer to as sentiment targets). Through a crowdsourcing study, we show that there are marked differences between the overall tweet sentiment and the sentiment expressed towards the subjects mentioned in tweets related to three crises events.

This paper presents a novel approach to perform sentiment analysis of news videos, based on the fusion of audio, textual and visual clues extracted from their contents. The proposed approach aims at contributing to the semiodiscoursive study regarding the construction of the ethos (identity) of this media universe, which has become a central part of the modern-day lives of millions of people. To achieve this goal, we apply state-of-the-art computational methods for (1) automatic emotion recognition from facial expressions, (2) extraction of modulations in the participants' speeches and (3) sentiment analysis from the closed caption associated to the videos of interest. More specifically, we compute features, such as, visual intensities of recognized emotions, field sizes of participants, voicing probability, sound loudness, speech fundamental frequencies and the sentiment scores (polarities) from text sentences in the closed caption. Experimental results with a dataset containing 520 annotated news videos from three Brazilian and one American popular TV newscasts show that our approach achieves an accuracy of up to 84% in the sentiments (tension levels) classification task, thus demonstrating its high potential to be used by media analysts in several applications, especially, in the journalistic domain.

An overwhelming amount of data is generated everyday onsocial media, encompassing a wide spectrum of topics. With almost every business decision depending on customer opinion, mining of social media data needs to be quick and easy.For a data analyst to keep up with the agility and the scale of the data, it is impossible to bank on fully supervised techniques to mine topics and their associated sentiments from social media. Motivated by this, we propose a weakly supervised approach (named, TweetGrep) that lets the data analyst easily define a topic by few keywords and adapt a generic sentiment classifier to the topic – by jointly modeling topics and sentiments using label regularization. Experiments with diverse datasets show that TweetGrep beats the state-of-the-art models for both the tasks of retrieving topical tweet sand analyzing the sentiment of the tweets (average improvement of 4.97% and 6.91% respectively in terms of area under the curve). Further, we show that TweetGrep can also be adopted in a novel task of hashtag disambiguation, which significantly outperforms the baseline methods.