Tone check your communication with Watson - Watson

#artificialintelligence

How many times have you sat in front of your laptop and read over your email worried about how your email would be interpreted by the recipient? Or spent hours and hours working on a press release, concerned that the tone may not be aligned with your target objective? These are just a few of the challenges people experience on a daily basis and what inspired us to develop the latest beta API on Watson Developer Cloud, Tone Analyzer. We are constantly communicating with people through text, which can leave room for frequent misunderstandings. Tone Analyzer is a service designed to help people assess and refine the tone in their communication.


Sentiment, emotion, attitude, and personality, via Natural Language Processing - IBM Watson

#artificialintelligence

It's a privilege to have Rama Akkiraju, IBM distinguished engineer and master inventor, participate as a Vision and Opportunity panelist at the 2016 Sentiment Analysis Symposium. I organize the symposium – this year's event takes place July 12 in New York – and recognize the many ways IBM has, over the years, expanded what's possible in the realm of what I'd characterize as "human data." "My team at IBM has been focused on developing technology to better understand people at a deeper level based on sentiment, emotion, attitude, and personality," said Rama. "With our work with Watson APIs – such as Tone Analyzer, Personality Insights, Emotion Analysis, and Sentiment Analysis – we're working to enable more compassion, engagement, and personalization in conversations across various channels." IBM's Marie Wallace, a 2014 sentiment symposium speaker, relates in a blog article that she "joined IBM in 2001 to build the next generation of NLP technology for IBM… the 3rd generation of IBM LanguageWare, which initially started back in the '80s." And I wrote, myself, in a 2008 InformationWeek article, BI at 50 Turns Back to the Future, about 1950s work by IBM researcher Hans Peter Luhn on the creation of business intelligence via text analysis.


Top 20 APIs You Should Know In AI and Machine Learning

#artificialintelligence

Application Programming Interface is a ready-made code to simplify the life of a programmer. It helps to digitize monotonous tasks and automate a whole slew of complex functions, which results in cutting down the cost of production. When it comes to AI / ML programming, we deal with integrating commercial APIs into existing platforms. It enables to interact with current code snippet, interact with each other and of course interact with your user-base. In this article, I've generously listed my favorites one APIs, which I consider the most suitable for AI and ML programming.


Inferring Latent User Properties from Texts Published in Social Media

AAAI Conferences

We demonstrate an approach to predict latent personal attributes including user demographics, online personality, emotions and sentiments from texts published on Twitter. We rely on machine learning and natural language processing techniques to learn models from user communications. We first examine individual tweets to detect emotions and opinions emanating from them, and then analyze all the tweets published by a user to infer latent traits of that individual. We consider various user properties including age, gender, income, education, relationship status, optimism and life satisfaction. We focus on Ekman’s six emotions: anger, joy, surprise, fear, disgust and sadness. Our work can help social network users to understand how others may perceive them based on how they communicate in social media, in addition to its evident applications in online sales and marketing, targeted advertising, large scale polling and healthcare analytics.


Multimodal Sentiment Analysis To Explore the Structure of Emotions

arXiv.org Machine Learning

We propose a novel approach to multimodal sentiment analysis using deep neural networks combining visual analysis and natural language processing. Our goal is different than the standard sentiment analysis goal of predicting whether a sentence expresses positive or negative sentiment; instead, we aim to infer the latent emotional state of the user. Thus, we focus on predicting the emotion word tags attached by users to their Tumblr posts, treating these as "self-reported emotions." We demonstrate that our multimodal model combining both text and image features outperforms separate models based solely on either images or text. Our model's results are interpretable, automatically yielding sensible word lists associated with emotions. We explore the structure of emotions implied by our model and compare it to what has been posited in the psychology literature, and validate our model on a set of images that have been used in psychology studies. Finally, our work also provides a useful tool for the growing academic study of images - both photographs and memes - on social networks.