The idea of creating/refining algorithms to perform some version of qualitative coding is not new or novel, although the practice does not seem yet to be widespread enough for people to consider it routine. I suspect this is due in part to the fact that many people who do research have been trained to be project managers, rather than technicians, and many technicians focus on methods for their own sake, so are not in the habit of thinking through research questions and designs to the extent needed to publish or fund a project. And, as an aside, I like to think of myself as a little more of a generalist or maybe "working supervisor" is more apt. I also think methods training is more important in a graduate degree than subject matter training. I suspect many of my colleagues differ in their views. But, to return to my subject matter of interest for this post - I want to begin by acknowledging that many qualitative researchers have described, in writing or in conversation, the reasons why a program cannot code or analyze data as well as a human. A recent experience with (human) coding of a biggish data set reminded me of several of these. Things that are difficult to recognize just from contextual and adjacent language (which is a lot of what algorithms and machine learning - to refine algorithms - rely on) include sarcasm, irony, exaggeration, some humor, and simple errors (although the latter is probably the quickest category of nuance that is mastered - look at the reasonable performance of spell checker programs). I suspect algorithms may struggle with certain malapropisms - I know I do when I encounter these in student papers!
In my own recent experiences, however, I observed the critical role of one's own context and experiences. As an example, a group analyzed trends in some data that described punishment. When I was a young person, being grounded - which I assume came from restrictions placed on pilots or flights (and, as another aside, this is in fact what the Wikipedia entry describes) - meant being unable to go out. Interestingly, more recently, I have seen "grounded from" applied to any type of limitation ("grounded from your phone"), so clearly the meaning of this term, at least in informal communications, is changing. Younger people recognized this but it took me some time and a few examples to see what was going on. Along with this there is an entirely alternative meaning of being "grounded" as in being centered, etc. What I have found is that sometimes you have to look hard for contextual clues - and even use a little intuition - to really interpret written or spoken language. But just participating in a few conversations where multiple skilled analysts with good language skills, mull over exactly what is meant by something, illustrates how complicated and challenging interpretation can be. I need to admit that I personally like the idea of automating analysis - especially analysis of large bits of information. I think algorithms to assess trends, their timing, and evolution - especially the specific times or bits of information that shift responses - are immensely useful and hand coding of tweets or other social media is an unnecessarily time consuming approach to gauge these things. I think the best use for coding-by-algorithm is when a surface level trend analysis of many thin data samples is desired. The cultural reference that usually pops into my head as I ponder big data is the scene in the original Matrix movie, where Joe Pantoliano's character is showing the Matrix to Keanu Reeves's character - and describes what he sees as not code but "blond, brunette, readhead..." The graphic - a screenshot of R - was inspired by that reference. I customized the color scheme on my desktop version to remind me of some of my original experiences with terminal/mainframe technology.
28 Comments
9/5/2022 07:01:31 am
Really informative article, I had the opportunity to learn a lot, thank you. https://freecodezilla.net/wpforms-pro-plugin-free-download/
Reply
9/11/2022 03:02:53 pm
Really informative article, I had the opportunity to learn a lot, thank you. https://kurma.website/
Reply
9/14/2022 04:10:57 pm
Really informative article, I had the opportunity to learn a lot, thank you. https://bit.ly/site-kurma
Reply
9/30/2022 09:00:04 am
It's great to have this type of content. Good luck with your spirit. Thank you. https://bit.ly/site-kurma
Reply
10/4/2022 02:50:32 pm
I think this post is useful for people. It has been very useful for me. Looking forward to the next one, thank you. https://escortnova.com/escort-ilanlari/kirsehir-escort/cicekdagi-escort/
Reply
10/5/2022 01:06:36 pm
It was a post that I found very successful. Good luck to you. https://escortnova.com/escort-ilanlari/istanbul-escort/sancaktepe-escort/
Reply
10/6/2022 01:03:53 am
I follow your posts closely. I can find it thanks to your reliable share. Thank you. https://escortnova.com/escort-ilanlari/kayseri-escort/yesilhisar-escort/
Reply
10/6/2022 09:43:52 am
I support your continuation of your posts. I will be happy as new posts come. Thank you. https://escortnova.com/escort-ilanlari/giresun-escort/kesap-escort/
Reply
10/8/2022 01:08:30 am
Thank you for your sharing. I must say that I am successful in your content. https://escortnova.com/escort-ilanlari/erzincan-escort/
Reply
10/8/2022 11:23:38 am
Thoughtful and real content is shared. Thank you for these shares. https://escortnova.com/escort-ilanlari/bursa-escort/gemlik-escort/
Reply
11/22/2022 11:44:20 am
Hemen Göz At evde para kazanmaya basla: https://sites.google.com/view/evden-ek-is/
Reply
12/10/2022 09:39:04 am
Düşmeyen bot takipçi satın al: https://takipcialdim.com/
Reply
12/10/2022 11:53:58 am
İnstagram beğeni takipçi satın al: https://takipcialdim.com/instagram-begeni-satin-al/
Reply
12/10/2022 11:54:22 am
Garantili Tiktok takipçi satın al: https://takipcialdim.com/tiktok-takipci-satin-al/
Reply
12/16/2022 05:52:37 am
takipci satın almak için tıkla: https://takipcim.com.tr/
Reply
1/9/2023 06:17:53 am
100 tl deneme bonusu veren siteleri öğrenmek istiyorsan tıkla.
Reply
6/30/2023 04:12:13 pm
En iyi bilecik ilan sitesi burada. https://bilecik.escorthun.com/
Reply
Leave a Reply. |
AuthorI am Sheryl L. Chatfield, Ph.D, C.T.R.S. I am a member of the faculty in the College of Public Health at Kent State University. I also Co-coordinate the Graduate Certificate in Qualitative Research and I am a member of the Design Innovation Team at Kent State. Archives
February 2024
Categories
|