Frequency of Grammatical Categories PER UTTERANCE

[Gahaam CHAN]

Dear Brian,

Thanks for your reply. As for why we want to get results for each 
utterance, I think it is because we don't want to 100% rely on automatic 
outputs. It is always necessary to go through the transcripts again, 
checking utterances one by one. For example, if we get some summary outputs 
about frequency of adjectives and corresponding exemplars, we still want to 
relocate to the original utterances to double check if it made correct 
classifications. It would be convenient if the results match well with the 
corresponding utterances. And then we can quickly check through the result 
outputs. Otherwise relocating the utterance is kind of troublesome 
sometimes. 

Jiahan
在2024年10月3日星期四 UTC+8 02:47:18<macw> 写道：

> Dear Jiahan,
>
> Yes, using *.cha will run on all files in a folder.
>
> Regarding your second requirement, the Excel outputs that CLAN creates 
> have the information in the @ID field in the first ten columns.
>
> Regarding the idea of an excel output with one line for every utterance, 
> this is not currently implemented in CLAN and I keep having trouble 
> understanding why one would want this level of detail. It would just make 
> further analysis very difficult. Maybe what you really want is to make use 
> of TalkBankDB.
>
> — Brian MacWhinney
> Teresa Heinz Professor of Cognitive Psychology, 
> Language Technologies and Modern Languages, CMU 
>
> > On Oct 2, 2024, at 1:50 AM, Gahaam CHAN <prean... at gmail.com> wrote:
> > 
> > Dear all,
> > 
> > Our group is trying to run frequency analysis of grammatical categories 
> on each utterance in multiple files. Ideally to get a file formatted as 
> below, may I ask if it is possible to get such an excel file by using CLAN 
> commands?<2.PNG>
> > • 
> > First, the commands should be run across different file by adding. To my 
> understanding, I can add *cha at the end of the command so that it will run 
> analysis on all of the chat file stored in the working directory.
> > • Second, I want to get a few columns to specify things like gender and 
> story name specified in the chat file. I am quite confused about how to do 
> it.
> > • Third and most importantly, I want to get frequency analysis PER 
> UTTERANCE with the utterances listed and frequencies of some grammatical 
> categories I specify in the command. Is there any way to do analysis on 
> utterance rather than on the whole file? What I can get so far is to an 
> excel file illustrating some information about frequencies of some 
> grammatical categories PER FILE (i.e. per story) as belows by running FREQ 
> commands on the mor line.<1-1.PNG>
> > Many thanks in advance! We would apprepriate any suggestions!
> > 
> > Regards,
> > Jiahan
> > 
> > 
> > -- 
> > You received this message because you are subscribed to the Google 
> Groups "chibolts" group.
> > To unsubscribe from this group and stop receiving emails from it, send 
> an email to chibolts+u... at googlegroups.com.
> > To view this discussion on the web visit 
> https://groups.google.com/d/msgid/chibolts/dd56958b-e6c1-4251-bc10-034fb43542c5n%40googlegroups.com
> .
> > <2.PNG><1-1.PNG>
>
>

-- 
You received this message because you are subscribed to the Google Groups "chibolts" group.
To unsubscribe from this group and stop receiving emails from it, send an email to chibolts+unsubscribe at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/chibolts/cb2ba684-7887-40c2-9d99-d9cbacd9aceen%40googlegroups.com.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/chibolts/attachments/20241002/f04bf037/attachment.htm>