Sentiment essentially relates to feelings; attitudes, emotions and opinions. Sentiment Analysis refers to the practice of applying Natural Language Processing and Text Analysis techniques to identify and extract subjective information from a piece of text. A person's opinion or feelings are for the most part subjective and not facts. Which means to accurately analyze an individual's opinion or mood from a piece of text can be extremely difficult. With Sentiment Analysis from a text analytics point of view, we are essentially looking to get an understanding of the attitude of a writer with respect to a topic in a piece of text and its polarity; whether it's positive, negative or neutral.

From virtual assistants to content moderation, sentiment analysis has a wide range of use cases. AI models that can recognize emotion and opinion have a myriad of applications in numerous industries. Therefore, there is a large growing interest in the creation of emotionally intelligent machines. The same can be said for the research being done in natural language processing (NLP). To highlight some of the work being done in the field, below are five essential papers on sentiment analysis and sentiment classification.

Dialogue response generation (DRG) is a critical component of task-oriented dialogue systems (TDSs). Its purpose is to generate proper natural language responses given some context, e.g., historical utterances, system states, etc. State-of-the-art work focuses on how to better tackle DRG in an end-to-end way. Typically, such studies assume that each token is drawn from a single distribution over the output vocabulary, which may not always be optimal. Responses vary greatly with different intents, e.g., domains, system actions. We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions. MoGNet consists of a chair generator and several expert generators. Each expert is specialized for DRG w.r.t. a particular intent. The chair coordinates multiple experts and combines the output they have generated to produce more appropriate responses. We propose two strategies to help the chair make better decisions, namely, a retrospective mixture-of-generators (RMoG) and prospective mixture-of-generators (PMoG). The former only considers the historical expert-generated responses until the current time step while the latter also considers possible expert-generated responses in the future by encouraging exploration. In order to differentiate experts, we also devise a global-and-local (GL) learning scheme that forces each expert to be specialized towards a particular intent using a local loss and trains the chair and all experts to coordinate using a global loss. We carry out extensive experiments on the MultiWOZ benchmark dataset. MoGNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, demonstrating its effectiveness for DRG.

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and employ annotation schemes with limited generalizability to conversations spanning multiple domains. To address these gaps, we created a new Response Quality annotation scheme, introduced five new domain-independent feature sets and experimented with six machine learning models to estimate User Satisfaction at both turn and dialogue level. Response Quality ratings achieved significantly high correlation (0.76) with explicit turn-level user ratings. Using the new feature sets we introduced, Gradient Boosting Regression model achieved best (rating [1-5]) prediction performance on 26 seen (linear correlation ~0.79) and one new multi-turn domain (linear correlation 0.67). We observed a 16% relative improvement (68% -> 79%) in binary ("satisfactory/dissatisfactory") class prediction accuracy of a domain-independent dialogue-level satisfaction estimation model after including predicted turn-level satisfaction ratings as features.

Should being comparable to BERT really be your goal here? The thing about BERT is that it wasn't really specifically designed for sentiment analysis. It just happens that it does that well too. But there's no reason to believe it's anywhere close to the "best way" to do sentiment analysis. I mean, as an analogy, pulling out a calculator to make a quick computation is often more convenient than booting up Matlab to do it, but using this fact to extol the merits of calculator kind of misses the point. If you want to describe how good your model is, you really should choose more relevant comparisons.

While it's not uncommon for small and medium-sized businesses (SMBs) to switch financial institutions, the 2019 FIS Performance Against Customer Expectations report has found that the rate of churn is increasing. Historically, 13%-15% of small and medium-sized firms have been found to be actively reviewing their banking relationships. However, the turnover rate has now risen to 61% among the top 50 U.S. banks and 60% among regional banks. All it may take to push an already skeptical firm to switch is one more bad experience. So customer sentiment analysis could be exactly what financial institutions need to improve customer experience -- ideally, before things ever reach that pass.

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast arrayof these resources, most under-resourced languages do not, especially for fine-grained sentiment tasks, such as aspect-level or targeted sentiment analysis. To improve this situation, we propose a cross-lingual approach to sentiment analysis that is applicable to under-resourced languages and takes into account target-level information. This model incorporates sentiment information into bilingual distributional representations, byjointly optimizing them for semantics and sentiment, showing state-of-the-art performance at sentence-level when combined with machine translation. The adaptation to targeted sentiment analysis on multiple domains shows that our model outperforms other projection-based bilingual embedding methods on binary targetedsentiment tasks. Our analysis on ten languages demonstrates that the amount of unlabeled monolingual data has surprisingly little effect on the sentiment results. As expected, the choice of a annotated source language for projection to a target leads to better results for source-target language pairs which are similar. Therefore, our results suggest that more efforts should be spent on the creation of resources for less similar languages tothose which are resource-rich already. Finally, a domain mismatch leads to a decreased performance. This suggests resources in any language should ideally cover varieties of domains.

Electronic Health Record (EHR) data can be represented as di screte counts over a high dimensional set of possible procedures, diagnoses, a nd medications. Supervised topic models present an attractive option for inco rporating EHR data as features into a prediction problem: given a patient's recor d, we estimate a set of latent factors that are predictive of the response variab le. However, existing methods for supervised topic modeling struggle to balance p rediction quality and coherence of the latent factors. W e introduce a novel approa ch, the prediction-focused topic model, that uses the supervisory signal to ret ain only features that improve, or do not hinder, prediction performance. By remov ing features with irrelevant signal, the topic model is able to learn task-relev ant, interpretable topics. W e demonstrate on a EHR dataset and a movie review dataset tha t compared to existing approaches, prediction-focused topic models are able to learn much more coherent topics while maintaining competitive prediction s.

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word tagging techniques respectively. Similar to adversarial attack problems with computer vision models discussed in existing literature, these intent-slot tagging models are often over-sensitive to small variations in input -- predicting different and often incorrect labels when small changes are made to a query, thus reducing their accuracy and reliability. However, evaluating a model's robustness to these changes is harder for language since words are discrete and an automated change (e.g. adding `noise') to a query sometimes changes the meaning and thus labels of a query. In this paper, we first describe how to create an adversarial test set to measure the robustness of these models. Furthermore, we introduce and adapt adversarial training methods as well as data augmentation using back-translation to mitigate these issues. Our experiments show that both techniques improve the robustness of the system substantially and can be combined to yield the best results.

Institutions may also consider building different machine learning models for the different regions, countries and languages they operate in.