Behavioral Signals logo



AI learns to play Chess via Comments

While up to now we've heard of AI learning to play chess by watching hundreds of moves played by world renowned players, it seems that's not the only way. It can learn to do the same by analyzing commentator sentiment. Enter SentiMATE, a chess algorithm developed by researchers Nicholas McCarthy, Isaac Kamlish and Isaac Bentata Chocron at the University College London. It evaluates the quality of chess moves by analyzing the reaction of expert commentators. The purpose was to prove you can use NLP to analyze sentiment and evaluate functions efficiently, like chess moves in this case. They started by building a classifier that extracts commentary describing the quality of Chess moves from large commentary datasets, and then created a sentiment analysis model trained on Chess commentary to accurately predict the quality of said moves. They then used both to evaluate the optimal next move of a Chess agent.

The researchers were surprised with SentiMATE, by its ability to work out some of the basic tenets of chess as well as several key strategies, such as forking and castling(chess terms). What we found fascinating is how thinking out of the box can produce the desired results on one hand, like learning AI to play chess, but could also be a great approach to teaching AI how to use sentiment for its learning.

Read more >



Communication Re-Imagined with Emotion AI

Discussing AI and Emotional Intelligence, Rana Gujral, CEO at Behavioral Signals, writes about the changes coming to AI and what it takes to create the well trained machine learning models that lead to successful emotionally aware AI.  He writes about how these systems are then able to analyze conversations and provide key insights into the nature and intent of someone’s inquiry based on how they speak and their facial and voice cues during a conversation. How support teams are better able to pinpoint angry customers and take action. Sales teams can analyze transcripts from calls to see where they might have lost a prospect. Human resources can implement smarter, more personalized training and coaching programs to develop their leadership bench. Read more >

Are Virtual Assistants the Future of Retail?

We've been noticing a number of new articles on how virtual assistants, smart speakers and chat bots can change retail. The specific article tackles online shopping (eCommerce) but we believe the change will affect brick-and-mortar stores, also. The post goes ahead explaining the basics, what are virtual assistants, which sectors in retail will be affected more (ex. food, entertainment) and adds some numbers, from Voicebot, as to how in the United States voice commerce sales are projected to jump to $40 Billion in 2022, from $1.8 Billion in 2017. Although the article has some inaccuracies and may have confused millions with billions what matters is it's hosted on an eCommerce related website. A brief search will yield several more articles which reveal the interest the sector is taking in Voice. We should expect much more in the coming months."  Read more >


3 Industries Being Transformed by Emotion AI

The next frontier of artificial intelligence is emotional. If we’re going to take AI seriously, it needs to understand who we really are and what makes us tick. After all, how smart is artificial intelligence if it doesn’t take into account how we feel? Discover why Emotional intelligence can be defined as “the global capacity of the individual to deal effectively with his environment.” When we translate this to AI, we allow computers to interpret our feelings and react appropriately, opening an entirely new world of possibilities that are already transforming a wide range of industries. If you want to discover how industries will be impacted by emotion AI read more >

Can AI Instill Emotions Into A Robot?

Bruce Sadiq writes in Europlat about AI and Emotional Intelligence. He notes that "...the emotional literacy gap between humans and bots is finally narrowing" and he states that "Artificial Intelligence (AI), although, it's superior to humans in terms of technology, it will take a lot of time and effort for AI to develop emotional intelligence (EI)". He goes ahead and lists the companies and startups already working in the field. Read more >



Voice Analysis Can Now Detect PTSD

PTSD is a pervasive mental health disorder that impacts between 11% and 20% of veterans who served in Afghanistan or Iraq, and that number might increase. We know that as many as 30% of Vietnam veterans have suffered from PTSD at some point in their lives. And it’s not just an affliction for armed services veterans. It’s estimated that 70% of adults will suffer some form of lasting trauma in their lives and as many as 12% will suffer from PTSD as a result. Conversational AI and voice analysis can help with daily monitoring and evaluation of PTSD patients and in turn, provide personalized insights to guide therapists. PTSD represents a spectrum of potential symptoms that can be hidden, amplified, or even lie dormant in patients who are struggling with significant trauma. 

Read more >



CBMI is organised by the Insight Centre for Data Analytics at the Dublin City University. CBMI 2019 aims at bringing together the various communities involved in all aspects of content-based multimedia indexing for retrieval, browsing, management, visualization and analytics. As active members of this community, our Senior Engineers will be there to showcase a demo on Using the Oliver API for emotion-aware movie content characterization, on Wednesday, 04/Sep, 3:30pm – 5:30pm at Poster & Demo Rooms. Be there and don’t miss it!
Date: September 4-6, 2019
City: Dublin, Ireland
Copyright © 2019 Behavioral Signals, All rights reserved.

Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

Email Marketing Powered by Mailchimp