For the past year, I’ve been invited to share some ideas on how bots can help newsrooms to deliver news and how to build an engaging chatbot experiences. And throughout these classes, I’ve also had challenging questions on how these technologies are pushing the boundaries of ethics, artificial intelligence and storytelling.
Below 3 takeaways for newsrooms that want to begin this chatbots journey.
Chatbots are on the first stage of experimenting through APIs, voice and messaging apps. However, last conferences such as the Web Summit in Portugal, the Chatbot Conference in Vienna or the API days in Barcelona have raised awareness on design and personalities to create more human interactions:
‘Ask yourself what personality you need for your chatbot’ @Chus9000 at #ApiDaysBCN pic.twitter.com/wL1P1EOusT
— Marian C Moldovan (@marianmoldovan) November 22, 2016
Efforts on choosing platforms or technologies to build chatbots shouldn’t override the conversation between the robot and a human. For this reason, accessing the chatbot is as important as drawing the conversation through flowcharts, mindmaps or storyboards. Could “Sorry, I didn’t understand your reply” be more friendly and approachable?
Instagram is an interesting platform that not only focuses on photography but also drawings. Below I have gathered some examples of chatbot storyboards that present customised scenarios between bots and users:
Telegram holds official bots and displays easy settings that help users without developing skills to build basic chatbots. On this previous post, I explained how I created three different bots through commands, menus, and submenus.
However, there are other tools that speed up the development of chatbots. For instance, Chatfuel. This platform runs the bot through an API Key, and administrators can create buttons and menus for a quick navigation.
I tested this platform creating a bot for the Noda and Tutki16 conference in Helsinki last April. This example acts similar to a channel, where subscribers receive notifications and news from several data streams:
On this post, I explain how to build it in three steps:
After some posts on how to build bots on Facebook, I got some feedback on making a difference between bots and chatbots. On a conversation with Miquel Serrabassa, Head of Technology at the Catalan newspaper La Nació Digital, he pointed out that some bots are, in fact, channels:
“These bots lack of interaction. They are unidirectional and post automated messages, but people cannot chat with them.”
According to Telegram, users interact with bots through messages, commands and inline requests controlled by a developer (and an API). From this definition, examples can be as broad as newspaper notifications, weather forecasts, and quiz games.
I have been experimenting and testing Telegram bots with basic coding skills and this is what I’ve learned so far:
Journalism, data and tech 