Building on the machine learning tools it unveiled earlier this year, Google Cloud Platform on Wednesday announced it's launching two machine learning APIs into open beta. The new Google Cloud Natural Language API allows a user to reveal the structure and meaning of text. Google promises support for a variety of languages, starting with English, Spanish, and Japanese. In a separate blog post, Google demonstrated how the Natural Language API could be used to analyze stories from the New York Times. In another example, digital marketers could use the API's sentiment analysis capabilities to monitor online product reviews or customer calls to service centers.

"How to choose the best topic model?" is the #1 question on our community mailing list. At RaRe Technologies I manage the community for the Python open source topic modeling package gensim. As so many people are looking for the answer, we've recently released an updated gensim 0.13.1 incorporating several new exciting features which evaluate if your model is any good, helping you to select the best topic model. Topic modeling is a technique for taking some unstructured text and automatically extracting its common themes, using machine learning. It is a great way to get a bird's eye view on a large text collection.

There are six main types of stories in fiction. That's what computer scientists found after teaching a machine to map the emotional arc of a huge corpus of literature. The overall research they did is fascinating (I wrote about it in greater detail here), but several smaller components of the work are compelling in their own right. To prepare a machine to carry out a sentiment analysis, for instance, computer scientists had to assign a happiness index to 10,222 individual words. That way, as the machine scanned passages from books, it could assess the emotional arc of the narrative.

This talk presents unsupervised analysis techniques that can be applied to collections of unstructured text documents for the purpose of discovering hidden topical trends, correlations or anomalies in their data. The techniques presented are applicable to a wide range of document types including news stories, technical blogs, customer feedback forms, congressional records, and legal documents, among many, many others. The talk will include introductory descriptions of the processing techniques needed to pre-process text data, discover salient multi-word phrases, and learn latent topic models describing the topical content of a collection of text data. The primary focus of the talk will be on analytic techniques that can be applied to the output of a latent topic model to extract trending topics over time, uncover topical correlations with other document features or meta-data, and discover anomalies in a text corpus. To illustrate these techniques, examples using news wire and congressional record data will demonstrate how important events in news wire data and anomalous congressional actions and interesting correlations can be discovered automatically using the presented unsupervised techniques.

The consumer sentiment analysis of this one's pretty easy, but will they be compensated? When a person feels sufficiently wronged to lodge a complaint with the Consumer Financial Protection Bureau (CFPB), there's likely to be some negative sentiment involved. But is there a connection between the language they use and the likelihood they will be compensated by the offending company? At the upcoming Sentiment Analysis Symposium, I will discuss how machine learning and rule-based sentiment analysis can support each other in a complementary analysis, and produce actionable information from large amounts of free form text. In this case, machine learning and sentiment analysis could improve and evolve the CFPB's ability to assess consumer complaints.

Cognovi Labs is a new analytics startup that relies on Twitris, a Wright State University-developed tool that claims to be able to take a sample of social media chatter about a specific topic and deduce real-time, large-scale, automated sentiment about the specific topic they are researching. As a real-world example of the tool's capability, the Cognovi Labs research team -- led by Wright State University researcher (and Cognovi Labs inventor) Dr. Amit Sheth -- analyzed Twitter chatter leading up to the Great Britain/European Union Membership Referendum (Brexit) on June 23. The team was able to predict some six hours before the news broke that the polls leaning toward the "remain" camp were incorrect. This was predicted by running Twitter chatter through the Cognovi Labs Twitris tool. The machine learning tool leverages Cognovi Labs' semantic intellectual property to be able to automate and extract aggregate meaning from social media chatter (including slang) in new, more precise ways.

Getting Artificial Intelligence programming knowledge is an excellent way to make you stand out in the workforce. Many even make entire careers out of it. AI programmers are some of the most sought after professionals across many industries all over the world. Now, you can learn AI programming online with the complete machine learning course bundle. You'll learn valuable skills like Quant trading, Hadoop, Object-oriented Java, NLP in Python, Twitter sentiment analysis and so many more.

We are interested in estimating individual labels given only coarse, aggregated signal over the data points. In our setting, we receive sets ("bags") of unlabeled instances with constraints on label proportions. We relax the unrealistic assumption of known label proportions, made in previous work; instead, we assume only to have upper and lower bounds, and constraints on bag differences. We motivate the problem, propose an intuitive formulation and algorithm, and apply our methods to real-world scenarios. Across several domains, we show how using only proportion constraints and no labeled examples, we can achieve surprisingly high accuracy. In particular, we demonstrate how to predict income level using rough stereotypes and how to perform sentiment analysis using very little information. We also apply our method to guide exploratory analysis, recovering geographical differences in twitter dialect.

Sentiment analysis is already an important component of many brands' social media strategies, but it can often be limited to basic interpretations of whether a conversation is positive, negative or neutral. At the Cannes Lions international advertising festival in June, data visualization technology provider Buzz Radar conducted an experiment that took sentiment analysis further, diving deeper into different types of emotional nuances. Patrick Charlton, director and co-founder of Buzz Radar, spoke to eMarketer's Maria Minsker just before the festival about what the company hoped to learn from the project. Patrick Charlton: Burberry has used our Command Center platform to look at conversations on social media surrounding their campaigns. We pull in every single mention of Burberry from conversations about London Fashion Week, for example, and analyze the sentiment.

For a more technical explanation, this and this article can be read. Here you can find a good explanation as well as a list of the mostly used Kernel functions.