Ever since British economist John Maynard Keynes first declared that investors are prey to people's urge to act, however irrationally, the financial world has tried to quantify the impact of public sentiment on stock prices. Solving the puzzle would give investors in the know a huge advantage over the competition. Over the past decade, one vibrant corner of that still ongoing research has been data analysis. The goal has been to tease out clues about sentiment that are hidden in news articles, regulatory filings, transcripts, and press releases. With the rise of artificial intelligence, the sophistication of sentiment-measuring technology is increasing.

In many review classification applications, a fine-grained analysis of the reviews is desirable, because different segments (e.g., sentences) of a review may focus on different aspects of the entity in question. However, training supervised models for segment-level classification requires segment labels, which may be more difficult or expensive to obtain than review labels. In this paper, we employ Multiple Instance Learning (MIL) and use only weak supervision in the form of a single label per review. First, we show that when inappropriate MIL aggregation functions are used, then MIL-based networks are outperformed by simpler baselines. Second, we propose a new aggregation function based on the sigmoid attention mechanism and show that our proposed model outperforms the state-of-the-art models for segment-level sentiment classification (by up to 9.8% in F1). Finally, we highlight the importance of fine-grained predictions in an important public-health application: finding actionable reports of foodborne illness. We show that our model achieves 48.6% higher recall compared to previous models, thus increasing the chance of identifying previously unknown foodborne outbreaks.

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However, existing memory networks do not perform well when leveraging heterogeneous information from different sources. In this paper, we propose a novel and versatile external memory networks called Heterogeneous Memory Networks (HMNs), to simultaneously utilize user utterances, dialogue history and background knowledge tuples. In our method, historical sequential dialogues are encoded and stored into the context-aware memory enhanced by gating mechanism while grounding knowledge tuples are encoded and stored into the context-free memory. During decoding, the decoder augmented with HMNs recurrently selects each word in one response utterance from these two memories and a general vocabulary. Experimental results on multiple real-world datasets show that HMNs significantly outperform the state-of-the-art data-driven task-oriented dialogue models in most domains.

One of the problems our Innovations team is working on at Socialbakers is sentiment analysis. Sentiment analysis is an automated process of recognition of how an audience feels towards any given subject from written or spoken language. It is one of the most common classification tools exploiting artificial intelligence. Sentiment analysis algorithm analyzes given text and predicts whether the underlying sentiment is positive, neutral or negative. Socialbakers is a global AI-powered social media marketing company and there are many use cases for sentiment analysis in our marketing software-as-a-service platform, called the Socialbakers Suite.

Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze emotions in conversations is challenging, partly because humans often rely on the context and commonsense knowledge to express emotions. In this paper, we address these challenges by proposing a Knowledge-Enriched Transformer (KET), where contextual utterances are interpreted using hierarchical self-attention and external commonsense knowledge is dynamically leveraged using a context-aware affective graph attention mechanism. Experiments on multiple textual conversation datasets demonstrate that both context and commonsense knowledge are consistently beneficial to the emotion detection performance. In addition, the experimental results show that our KET model outperforms the state-of-the-art models on most of the tested datasets in F1 score.

Our platform archives the crypto assets historical data, absorb the news feed, generate trading signals in real-time and finally make the decision to buy, sell or hold. Our bots based on these signals trade automatically on third-party exchanges using your own accounts. The AI engine makes use of Technical Analysis, Sentiment Analysis along with our 10 unique strategies, to make the most accurate predictions of the market using Machine Learning.

Artificial Intelligence is one of the most innovative technological breakthroughs of the modern times. From daily lives to corporate cultures, everything is being impacted by the novel technology. Artificial Intelligence (AI) strategically improves business processes by giving managers the power to analyze a vast amount of valuable data derived from customers as well as employees. When it comes to human resources, AI is particularly solving one of the greatest issues managers have been facing for many years- to improve employee engagement and retention rates. AI has the potential to give managers the power to make a better workplace, where employees don't feel distracted or dissatisfied with their job roles.

Hierarchical neural networks are often used to model inherent structures within dialogues. For goal-oriented dialogues, these models miss a mechanism adhering to the goals and neglect the distinct conversational patterns between two interlocutors. In this work, we propose Goal-Embedded Dual Hierarchical Attentional Encoder-Decoder (G-DuHA) able to center around goals and capture interlocutor-level disparity while modeling goal-oriented dialogues. Experiments on dialogue generation, response generation, and human evaluations demonstrate that the proposed model successfully generates higher-quality, more diverse and goal-centric dialogues. Moreover, we apply data augmentation via goal-oriented dialogue generation for task-oriented dialog systems with better performance achieved.

Dialogue state tracking, or estimating and keeping tabs on a person's goals throughout a multiturn conversation, is one of the ways Alexa figures out what users want. By combining conversation history with the most recent command, Amazon's intelligent assistant can better map slot names -- the price of a hotel or its star rating, for example -- to slot values, or entities mentioned in a dialogue. Alexa already performs dialogue state tracking pretty effectively, but a team of scientists at Amazon's R&D division think there's room for improvement. In a new paper ("Dialog State Tracking: A Neural Reading Comprehension Approach") scheduled to be presented at the International Speech Communication Association's Special Interest Group on Discourse and Dialogue, they propose an AI system that formulates dialogue state tracking as a classic question-answering problem. In other words, their machine learning model decides on the slot value for each slot name after reading a conversational passage. The team reports that their technique yielded a 6.5% improvement in slot tracking accuracy over the previous state of the art in qualitative tests and that it had an accuracy of up to 96% per slot on a data set of development data.

Understanding how political attention is divided and over what subjects is crucial for research on areas such as agenda setting, framing, and political rhetoric. Existing methods for measuring attention, such as manual labeling according to established codebooks, are expensive and can be restrictive. We describe two computational models that automatically distinguish topics in politicians' social media content. Our models---one supervised classifier and one unsupervised topic model---provide different benefits. The supervised classifier reduces the labor required to classify content according to pre-determined topic list. However, tweets do more than communicate policy positions. Our unsupervised model uncovers both political topics and other Twitter uses (e.g., constituent service). These models are effective, inexpensive computational tools for political communication and social media research. We demonstrate their utility and discuss the different analyses they afford by applying both models to the tweets posted by members of the 115th U.S. Congress.