Blog: Information Architecture (IA) in Machine Learning
In the world of UX design, users find digital products easy to use because they are well structured. This doesn’t happen unintentionally, but it is the result of good IA.
Information architecture (IA) is a science of organizing and structuring information or content, including text, photos and videos within a digital product. IA helps people to understand where they are, what’s around and what to expect.
A good IA is findable, accessible, clear, communicative, useful, credible, controllable, valuable, learnable and delightful.
IA in Machine learning
Over the past decade, Artificial Intelligence (AI) has been a buzzword. Machine learning is part of AI. Machine learning automates analytical model building and deals with a huge amount of data. A good IA can help the machine to better interpret the data, find patterns and ultimately learn. Without good IA, a machine learning model would not be successful.
Voice User Interface (VUI) has gained popularity over recent years. VUI uses machine learning to achieve speech recognition technology. VUI allows users to speak to devices, in turn, to understand and act upon users’ commands.
Voice assistants like Siri, Alexa, Google Home are popular examples of VUI. I own a Google Home assistant with screen, from time to time I’d ask him about the weather, good restaurants near by, or set a reminder for me. He does a great job for setting a reminder, he would ask me what day and what time I’d like to be reminded. This is an example of how IA is used in VUI.
Although nowadays, VUI is believed to reach 90% accuracy, there are still frustrating moments when you talk to a voice assistant. This is where IA comes into play, in order to improve VUI, devices should understand conversation flow. A numerous voice scripts need to be organized and constantly adapted.
Information architecture is an essential part of the powerful user experience design. Efficient IA helps users navigate through digital products easily.