Personal/national mood tracker: Difference between revisions

From Computer Laboratory Group Design Projects
Jump to navigationJump to search
(Created page with " I have received the following proposals from Tomas Cervenka at VisualDNA. Tomas is the contact person (tomas@visualdna.com) Predicting personality and detecting cheaters At V...")
 
No edit summary
 
(2 intermediate revisions by the same user not shown)
Line 1: Line 1:
Client: Tomas Cervenka, VisualDNA <tomas@visualdna.com>


I have received the following proposals from Tomas Cervenka at VisualDNA.
National wellbeing is the aggregate of the population mood, but it's difficult to know whether mood estimates are accurate or not. In fact, even individuals find it difficult to estimate how their mood has changed over time. The goal of this project is to automatically estimate a number of factors that effect national mood - news, weather, economic indicators - and aggregate these with personal mood estimates measured via your mobile phone's sensors. These could include movement or orientation data (facing into the wind?), feeds from a Facebook profile, or other data. If users are unsure what mood they are in, they can check their phone. And a longitudinal graph might help to review the year, or forecast important mood transitions - like when the end of term is approaching.
 
Tomas is the contact person (tomas@visualdna.com)
 
Predicting personality and detecting cheaters
 
At VisualDNA we focus on profiling online users using our patented visual quizzes. Users are presented with a set of questions and have to answer by clicking one or more images. You will be given an extensive dataset and asked to build a model and a visual tool to predict user's answers based on answers he has already given in the quiz. The ultimate goal is to algorithmically predict, whether user's answers are genuine or user was trying to 'cheat' the quiz. If you can beat our existing model, there's an extra prize involved!
 
Inferring personality from behaviour
 
"Tell me what you eat, and I will tell you what you are" is an old quote - at VisualDNA we have a different one: "Tell me what sites you visit and I will tell you what you are". You will be given an extensive anonymised dataset of user's browsing history (no dodgy sites included, trust us) and asked to build a model and a tool to predict, based on asking users for a set of sites / pages they have recently visited, their demographic, socioeconomic and personality traits. If you can beat our existing model, there's an extra prize involved!

Latest revision as of 10:47, 25 October 2012

Client: Tomas Cervenka, VisualDNA <tomas@visualdna.com>

National wellbeing is the aggregate of the population mood, but it's difficult to know whether mood estimates are accurate or not. In fact, even individuals find it difficult to estimate how their mood has changed over time. The goal of this project is to automatically estimate a number of factors that effect national mood - news, weather, economic indicators - and aggregate these with personal mood estimates measured via your mobile phone's sensors. These could include movement or orientation data (facing into the wind?), feeds from a Facebook profile, or other data. If users are unsure what mood they are in, they can check their phone. And a longitudinal graph might help to review the year, or forecast important mood transitions - like when the end of term is approaching.

Retrieved from "https://wiki.cam.ac.uk/wiki/cl-design-projects/index.php?title=Personal/national_mood_tracker&oldid=162"