Adding machine learning to a serverless data analysis pipeline Google Cloud Big Data and Machine Learning Blog Google Cloud Platform

#artificialintelligence

In the right architecture, machine-learning functionality takes data analytics to the next level of value. Editor's note: This guest post (translated from Italian and originally published in late 2016) by Lorenzo Ridi, of Google Cloud Platform partner Noovle of Italy, describes a POC for building an end-to-end analytic pipeline on GCP that includes machine-learning functionality. "Black Friday" is traditionally the biggest shopping day of the year in the United States. Black Friday can be a great opportunity to promote products, raise brand awareness and kick-off the holiday shopping season with a bang. During that period, whatever the type of retail involved, it's also becoming increasingly important to monitor and respond to consumer sentiment and feedback across social media channels.


Analyzing the Political Sentiment of Tweets in Farsi

AAAI Conferences

We examine the question of whether we can automatically classify the sentiment of individual tweets in Farsi, to determine their changing sentiments over time toward a number of trending political topics. Examining tweets in Farsi adds challenges such as the lack of a sentiment lexicon and part-of-speech taggers, frequent use of colloquial words, and unique orthography and morphology characteristics. We have collected over 1 million Tweets on political topics in the Farsi language, with an annotated data set of over 3,000 tweets. We find that an SVM classifier with Brown clustering for feature selection yields a median accuracy of 56% and accuracy as high as 70%. We use this classifier to track dynamic sentiment during a key period of Irans negotiations over its nuclear program.


Happy, Nervous or Surprised? Classification of Human Affective States in Social Media

AAAI Conferences

Sentiment classification has been a well-investigated research area in the computational linguistics community. However, most of the research is primarily focused on detecting simply the polarity in text, often needing extensive manual labeling of ground truth. Additionally, little attention has been directed towards a finer analysis of human moods and affective states. Motivated by research in psychology, we propose and develop a classifier of several human affective states in social media. Starting with about 200 moods, we utilize mechanical turk studies to derive naturalistic signals from posts shared on Twitter about a variety of affects of individuals. This dataset is then deployed in an affect classification task with promising results. Our findings indicate that different types of affect involve different emotional content and usage styles; hence the performance of the classifier on various affects can differ considerably.


Everything Google announced at its 2017 I/O conference

#artificialintelligence

During a non-stop, two-hour keynote address at its annual I/O developers conference, Google unveiled a barrage of new products and updates. Here's a rundown of the most important things discussed: Google CEO Sundar Pichai kicked off the keynote by unveiling a new computer-vision system coming soon to Google Assistant. Apparently, as Pichai explained, you'll be able to point your phone's camera at something, and the phone will understand what it's seeing. Pichai gave examples of the system recognizing a flower, a series of restaurants on a street in New York (and automatically pulling in their ratings and information from Google), and the network name and password for a wifi router from the back of the router itself--the phone then automatically connecting to the network. Theoretically, in the future, you'll be searching the world not through text or your voice, but by pointing your camera at things.


Tech majority disagrees with AI warnings from Hawkings, Musk and Gates

#artificialintelligence

Tech star personalities Stephen Hawkings, Elon Musk and Bill Gates warned the public about artificial intelligence (AI). The tech-oriented public and AI experts disagree, though, according to a recent research paper, "Tweeting AI: Perceptions of AI-Tweeters (AIT) vs Expert AI-Tweeters (EAIT)," (pdf) published by researchers at the School of Computing, Informatics and Decision Systems Engineering at the University of Arizona. "Co-occurring patterns tell us that AIT are in general fantasizing about the future whereas EAIT are grounded and realistic." Study authors used statistical analysis, sentiment analysis and machine learning to learn this insight and summarize the study with the conclusions below. Despite the overall negative sentiment of Twitter, overall the 2.3 million tweets analyzed about AI are positive by a large margin.