To help automate and keep track of online communities mentioning certain keywords in realtime, a bespoke system called Radar was built using the latest technologies; machine learning, natural language processing, laravel combed with VueJS.
The system communicates with a series of Radar scanners (raspberry pi) that loads the selected website in the browser that is controlled via a bespoke plugin that periodically checks for the given keywords. If a match is found, an alert is sent back to the system. From here, the system will perform some cleaning tasks; such as encoding, filtering out rude words and discarding posts that are duplicates or retweets. The next task is to broadcast the new alert to users logged in. If the user has selected the option for email alerts then an email will be sent of the alert. Similarly; the alert will be sent to the chosen API if the option is selected.
A number of scheduled tasks run periodically; one of the priority tasks involves performing predictions on whether the alert is interesting based on previous alerts that have been marked as interesting; another task performs sentiment analysis that rates the emotion of the alert as to whether its negative or positive. And one of the last tasks checks whether any of the new alerts are similar to any of the last 100 alerts – this is useful for detecting trends.
* There are a number of tasks which haven’t been mentioned to protect the intelligence of the system
If you’re looking for similar cornwall bespoke systems, whether its a bespoke system to automate your business processes or you are interested in having a similar digital drinks menu created, then please feel free to contact me by visiting my contact page here.