Page 333 -

322 CHAPTER 11 Analyzing qualitative data

and voice activity detection (Xue et al., 2006). A substantial number of studies have
focused on automatic annotation and management of images.
In addition to the automatic annotation applications, a number of other tools have
been developed to facilitate the process of multimedia content analysis. Dragicevic
et al. (2008) developed a direct manipulation video player that allows a video ana-
lyst to directly drag and move the object of interest in the video to specific loca-
tions along their visual trajectory. Wilhelm et al. (2004) developed a mobile media
metadata framework that enables image annotation on a mobile phone as soon as a
picture is taken. The unique feature of this system is that it guesses the content of the
picture for the purpose of reducing the amount of text entry needed during the an-
notation. Kandel et al. (2008) proposed the PhotoSpread system, which allows users
to organize and analyze photos and images via an easy-to-use spreadsheet with direct
manipulation functions. Applications that support content visualization for easy data
sharing and analysis have also been developed (Cristani et al., 2008). The ChronoViz
tool supports playback and review of multiple, synchronized streams of multimedia
data (Fouse et al., 2011).
Techniques for automatic annotation still need substantial advancements in order
to achieve reliable coding. The applications to facilitate manual coding have shown
promising results but improvements are also needed to improve the usability and
reliability of those systems.

11.6 SUMMARY

Text, multimedia, and other qualitative data are important sources of informa-
tion for HCI researchers and practitioners. The procedure and techniques com-
monly used to analyze qualitative data are quite different from those applied to the
analysis of quantitative data. Probably the most unique characteristic of content
analysis is that it involves human coding. The absence of numeric data and direct
measures makes qualitative data analysis more susceptible to biased interpreta-
tion or subjective manipulation. Therefore, it is critical to adopt well established
procedures and techniques to ensure high-quality analysis that is both valid and
reliable. Although there is disagreement regarding its implementation process and
guidelines, grounded theory is widely used for qualitative data analysis. The major
difference between grounded theory and other qualitative research strategies is its
emphasis on theory development in continuous interplay between data collection
and data analysis.
When analyzing text content, we need to develop a set of coding categories that
accurately summarizes the data or describes the underlying relationships or patterns
buried in the data. Depending on the specific context of the research question, a
priori coding or emergent coding may be used to generate the coding categories. In
order to produce high-quality coding, multiple coders are usually recommended to
code the data. During the coding process, the coders should constantly look for state-
ments likely to carry valuable information, ask questions about the data, and make