Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

Ethno-Mining: Integrating Numbers and Words from the Ground Up

Ryan Aipperspach, Tye Lawrence Rattenbury, Allison Woodruff, Ken Anderson, John F. Canny and Paul Aoki

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2006-125
October 6, 2006

http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-125.pdf

In this paper we present ethno-mining, a mixed methods approach drawing on techniques from ethnography and data mining. Ethno-mining is characterized by tight, iterative loops that integrate both the results and the processes of ethnographic and data mining techniques to interpret data. Ethno-mining provides two key benefits. First, it makes use of both qualitative and quantitative data (e.g. observations and sensor data) to study phenomena that are practically inaccessible through either data type alone. Second, it provides a means of interpreting that data which produces novel insights by exposing the biases inherent in either type of data alone. We present ethno-mining in the context of a study of mobility and laptop use in the home, discussing how findings from the study relate to the use of the method.


BibTeX citation:

@techreport{Aipperspach:EECS-2006-125,
    Author = {Aipperspach, Ryan and Rattenbury, Tye Lawrence and Woodruff, Allison and Anderson, Ken and Canny, John F. and Aoki, Paul},
    Title = {Ethno-Mining: Integrating Numbers and Words from the Ground Up},
    Institution = {EECS Department, University of California, Berkeley},
    Year = {2006},
    Month = {Oct},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-125.html},
    Number = {UCB/EECS-2006-125},
    Abstract = {In this paper we present ethno-mining, a mixed methods approach drawing on techniques from ethnography and data mining. Ethno-mining is characterized by tight, iterative loops that integrate both the results and the processes of ethnographic and data mining techniques to interpret data. Ethno-mining provides two key benefits. First, it makes use of both qualitative and quantitative data (e.g. observations and sensor data) to study phenomena that are practically inaccessible through either data type alone. Second, it provides a means of interpreting that data which produces novel insights by exposing the biases inherent in either type of data alone. We present ethno-mining in the context of a study of mobility and laptop use in the home, discussing how findings from the study relate to the use of the method.}
}

EndNote citation:

%0 Report
%A Aipperspach, Ryan
%A Rattenbury, Tye Lawrence
%A Woodruff, Allison
%A Anderson, Ken
%A Canny, John F.
%A Aoki, Paul
%T Ethno-Mining: Integrating Numbers and Words from the Ground Up
%I EECS Department, University of California, Berkeley
%D 2006
%8 October 6
%@ UCB/EECS-2006-125
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/2006/EECS-2006-125.html
%F Aipperspach:EECS-2006-125