Artificial intelligence is a wide-ranging tool that enables people to rethink how we integrate information, analyze data, and use the resulting insights to improve decision making—and already it is transforming every walk of life. Lets us look at how AI is all-pervasive.
We are living in a world where Artificial Intelligence (AI) is working to determine trends with search engines, and more. One specific area is where AI can now dictate and determine is which stories will go viral on social media. Yes, you read it right. AI is used to create viral content.
AI and its several uses
There are many AI models in development to mimic human actions. One of the AI-based machine learning tools dedicated to the job is MoneyLearn. You have to show it any kind of data you want and then categorize each one and it will learn from it, constantly improving. MoneyLearn does the ‘sentiment analysis’, where the tool when given a series of emails you have received, tells you if the tone is angry or happy. This can be used in looking into customer service tickets.
So how does MoneyLearn operate?
Get the data into a form that MonkeyLearn could use, to begin with. You can use Gmail messages, Facebook posts, RSS feeds, or just CSV files of data. There are two ways, one is more accurate and takes a lot more time, the other is less accurate and takes a few minutes. You’ll have to decide for yourself.
There is a technology with a built-in service called ‘email parser’, where you can send an email and show which parts of the email correspond to different types of data (much like machine learning). If you forward an email and highlight the name of each query and instruct it to consider that part of all future emails, you call the contact email and so on.
It’s tedious and you have to highlight each part of each query so that it will ‘scrape’ that data in the future. The good news is you only have to do this the first time. Once it’s scraping data, the tool can create its RSS feed, which you can then feed into MonkeyLearn.
Teaching MonkeyLearn what matters and what doesn’t is a task in itself. You can create a free account to get started and start to test. Plugin the RSS feed you have created or found, create your categories and then start categorizing those samples. Despite they asking for a minimum of 40, supplying more than the minimum count will fetch you better results. Also when you have categories that skew heavily a larger sample size is better. Once you go through a good number of samples, MonkeyLearn will have a sense of its accuracy. A mere 69 samples, resulted in an 87% accuracy rate for categorizing future samples.
Now, what do you do with that information?
Set up a Zap that started with that same RSS feed we created or found. The trigger was any new RSS feed item. The first action was to have MonkeyLearn classify text that would spit out an Interesting or Not Interesting label. The next step was to build a Zapier filter which says only to continue if the label does not contain ‘not’ and deliver those results as a Slack direct message.
The process is invariably on point and worth pursuing. It is a huge win and great use of technology that capitalizes on the platform’s capabilities and my input. It is not just information that is now more accessible but results as well.
The Next Level
If you want to create a PR machine for yourself, you can automate the pitch to each of these queries. You would simply add another filter to the zap and include a Gmail message step to finish it off. So you could say, once an interesting query is delivered if that query mentions entrepreneurs, you could automatically send a Gmail message with a standard pitch about your entrepreneurial journey. The result is a free, automated, publicist in a box.