{"id":68,"date":"2017-01-29T19:12:40","date_gmt":"2017-01-29T19:12:40","guid":{"rendered":"https:\/\/projects-old.etc.cmu.edu\/campfire\/?p=68"},"modified":"2017-01-29T19:12:40","modified_gmt":"2017-01-29T19:12:40","slug":"weeks-1-2-117-128-project-campfire","status":"publish","type":"post","link":"https:\/\/projects-old.etc.cmu.edu\/campfire\/index.php\/2017\/01\/29\/weeks-1-2-117-128-project-campfire\/","title":{"rendered":"Weeks 1& 2: 1\/17-1\/28: Project Campfire!"},"content":{"rendered":"

In weeks 1 and 2, the project, formally known as \u201cBard,\u201d renamed itself Campfire, and jumped into building both a technological foundation for our planned interactions as well as exploration into audio focused interactions. \u00a0Roy and Phan focused on the technology development, and Seth worked with Sarabeth on jumping into design.<\/span><\/p>\n

Roy and Phan brainstorm interaction foundation<\/figcaption><\/figure>\n

On the <\/span>technology<\/b> side, Roy and Phan started by putting together a high-level architecture on how the AI would accept user input, and output a response. \u00a0This involves taking in an input, and finding keywords, and finding intent from it in an initial encoding phase. \u00a0A hidden phase would next take these values from an encoding phase, and generate answer keywords and intent from the story to pass on to a decoding phase. \u00a0The decoding phase would initiate a query-based response system and dynamically generated responses on a neural network, to test the effectiveness of both.<\/span><\/p>\n

In addition, Roy tested out various machine learning libraries and APIs: Theano, TensorFlow, Keras and Chainer. \u00a0He and Phan decided to move ahead with TensorFlow + Keras. \u00a0Roy also spent time this week researching papers and learning more about the capabilities of RNNs and LSTMs, for developing language models, testing out a simple LSTM in generating text based on keyword inputs.<\/span><\/p>\n

Prototyping out necessary information for the first playtest<\/figcaption><\/figure>\n

For the <\/span>design<\/b> side, Phan developed a \u201cWizard of Oz\u201d Alexa setup for Sarabeth and Seth to test initial designs, in order to quickly prototype interaction cases. \u00a0Seth and Sarabeth spent the first week investigating story types, examples and scenarios, e.g. short stories, poems, fables, news, politics and sports. \u00a0They settled on starting with a recap interaction of the Pittsburgh Steelers AFC Championship game against the New England Patriots, which tragically (for Steelers nation) ended in defeat. \u00a0Their strategy for week 2 involved creating a library of information to pull from during a test with a few football fans in the ETC building. \u00a0The goal of this first playtest was to see how open ended questions, option based questions, prompts, responses, suggestions, trivia and fail cases affect the flow of conversation. \u00a0Though we ultimately want to develop an experience using a linear story, we started with a sports topic to start identifying what common threads we see in audio interactions. \u00a0<\/span><\/p>\n

With our first playtest (Thank you Cody (Pats fan), Mike (Bills fan) and Erika (not a fan)) we have several takeaways:<\/span><\/p>\n