Dialog state tracking is to accurately infer a compact representation of the dialog status up to the current turn, it needs to summarize all the dialog history information and user's goals. In a successful spoken dialog system, dialog state tracker is one of the most important components of the pipelines. Yet until recently, there are no general, flexible, accurate and truly end to end dialog state tracking models. In this paper, we propose a novel model named state tracking networks that can perform dialog state tracking in a natural efficient and elegant way. It uses an explicit gate to model the state updating mechanism and can be trained end to end in a deterministic manner using standard backpropagation techniques or stochastically by reinforcement learning. Our model can both deal with ASR and text input without any modification. We perform experiments on the Second Dialog State Tracking Challenge dataset(DSTC2) and get performance matching the state-of-the-art models. Furthermore, the qualitative analysis reveals that the gating mechanism learned by our model agree well with intuition.

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%).

For robots to effectively interact with human users, it is necessary that they recognize what people in the environment are doing. This is especially the case when robots are performing complementary tasks since the human users are not following any specific process. There is much uncertainty in how people act and the duration of time they need to perform their actions. In this work, we discuss the use of topic models for such plan and activity recognition tasks. We begin with the development of a domain-independent representation of human postural information obtained from RGB-D sensor data. This representation may be used with Latent Dirichlet Allocation (LDA) topic models as an integration of plan and activity recognition. This is followed by a proposition of extensions to LDA that allow temporal and object relational information to also be used in plan and activity recognition tasks.

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.

We propose a new pooling technique for topic modeling in Twitter, which groups together tweets occurring in the same user-to-user conversation. Under this scheme, tweets and their replies are aggregated into a single document and the users who posted them are considered co-authors. To compare this new scheme against existing ones, we train topic models using Latent Dirichlet Allocation (LDA) and the Author-Topic Model (ATM) on datasets consisting of tweets pooled according to the different methods. Using the underlying categories of the tweets in this dataset as a noisy ground truth, we show that this new technique outperforms other pooling methods in terms of clustering quality and document retrieval.

Location-based social sites, such as Foursquare or Yelp, are gaining increasing popularity. These sites allow users to check in at venues and leave a short commentary in the form of a micro-review. Micro-reviews are rich in content as they offer a distilled and concise account of user experience. In this paper we consider the problem of predicting the topic of a micro-review by a user who visits a new venue. Such a prediction can help users make informed decisions, and also help venue owners personalize users' experiences. However, topic modeling for micro-reviews is particularly difficult, due to their short and fragmented nature. We address this issue using pooling strategies, which aggregate micro-reviews at the venue or user level, and we propose novel probabilistic models based on Latent Dirichlet Allocation (LDA) for extracting the topics related to a user-venue pair. Our best topic model integrates influences from both venue inherent properties and user preferences, considering at the same the sentiment orientation of the users. Experimental results on real datasets demonstrate the superiority of this model compared to simpler models and previous work; they also show that venue-inherent properties have higher influences on the topics of micro-reviews.

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.

Sentiment analysis is the computational study of opinionated text and is becoming increasing important to online commercial applications. However, the majority of current approaches determine sentiment by attempting to detect the overall polarity of a sentence, paragraph, or text window, but without any knowledge about the entities mentioned (e.g.