Class notes
Human and Automatic Text Analysis - Samenvatting Hoorcolleges
- Course
- Institution
Samenvatting van alle hoorcolleges van het van Human and Automatic Text Analysis. Handmatige tekstanalyse + Computationele tekstanalyse.
[Show more]
Seller
Follownienkebreugelmans
Reviews received
Content preview
HUMAN AND AUTOMATIC TEXTANALYSIS
Inhoud
DEEL 1 - Handmatige Tekstanalyse
Hoorcollege 1 - Tekstanalyse.............................................................................................................. 4
Analyse............................................................................................................................................... 4
Hoorcollege 2 – Functionele analyse.................................................................................................. 5
Functionele analyse............................................................................................................................ 5
Wat zijn de theorieën die ten grondslag liggen aan de FA?................................................................5
Doelen herkennen............................................................................................................................... 7
Taalhandelingstheorie: Instrument voor lokale doelen........................................................................9
Theory of Planned Behavior (Ajzen, 1991).......................................................................................13
Procedure bij Functionele analyse.................................................................................................... 15
Hoorcollege 3 – Genre-analyse......................................................................................................... 15
Genre theorie.................................................................................................................................... 15
Biber (1989)...................................................................................................................................... 16
Model voor Genres: 3 ingebedde frames (Sinding, 2016).................................................................17
Stereotypie........................................................................................................................................ 17
Hoorcollege 4 – Lexicale Analyse..................................................................................................... 18
Semantische eigenschappen............................................................................................................ 18
Decompositie van woordbetekenis.................................................................................................... 19
Typen woordrelaties.......................................................................................................................... 20
Ketens............................................................................................................................................... 21
LA-instrument in stappen.................................................................................................................. 22
Lexicale analyse................................................................................................................................ 22
Tekstuele analyse 5 – Zonder & Met................................................................................................. 23
Referentie......................................................................................................................................... 23
Informatiestatus................................................................................................................................. 23
Anaforen........................................................................................................................................... 25
Centering.......................................................................................................................................... 26
Referentiële coherentie..................................................................................................................... 29
Lexicale analyse................................................................................................................................ 30
Hoorcollege 6...................................................................................................................................... 31
Accessibility theory............................................................................................................................ 31
Hoorcollege 1 – Computationele Lexicale Analyse (WordNet).......................................................32
, Relatedness, similarity, distance....................................................................................................... 33
Roget’s thesaurus............................................................................................................................. 33
Path-based similarity......................................................................................................................... 35
Leacoock & Chodorow’s normalized path length..............................................................................36
Wu & Palmer’s conceptual similarity................................................................................................. 37
Resnik’s information-based approach............................................................................................... 38
Jiang & Conraths’s combined approach............................................................................................ 39
Lin’s universal similarity measure...................................................................................................... 39
Lesk’s gloss-based similarity............................................................................................................. 39
Overzicht maten in B&H.................................................................................................................... 40
Evaluatie van similarity metrics......................................................................................................... 40
Budanitski & Hirst: Malapropismedetectie......................................................................................... 41
Samenvatting.................................................................................................................................... 44
Hoorcollege 2 – Leesbaarheidsanalyse (Deel 1)..............................................................................45
Leesbaarheidsformules..................................................................................................................... 45
Flesch-Kincaid grade level................................................................................................................ 45
Tekstbegrip....................................................................................................................................... 45
Gebruikte kenmerken voor leesbaarheidsanalyse in T-Scan...........................................................46
Type-Token Ratio (TTR)................................................................................................................... 47
Measure of Textual Lexical Diversity (MTLD)....................................................................................47
Cloze-test.......................................................................................................................................... 48
1. Individuele tekstkenmerken........................................................................................................... 49
2. Model als geheel........................................................................................................................... 50
Is tekstelement X veranderbaar?...................................................................................................... 50
Conclusies......................................................................................................................................... 50
Hoorcollege 3 – Leesbaarheidsanalyse (deel 2)..............................................................................51
Leesbaarheidsscores........................................................................................................................ 52
CAREC en CARES........................................................................................................................... 52
Coh-metrix......................................................................................................................................... 53
Situatiemodel.................................................................................................................................... 53
Temporele cohesie............................................................................................................................ 54
Intentionaliteit en causaliteit.............................................................................................................. 54
Corpusonderzoek Graesser et al...................................................................................................... 55
Conclusies......................................................................................................................................... 56
Hoorcollege 4 – Text Mining.............................................................................................................. 58
Woordfrequenties.............................................................................................................................. 58
Het Google Books-corpus................................................................................................................. 58
Onderzoeksvragen............................................................................................................................ 59
,Beperkingen van het corpus.............................................................................................................. 60
Casus 1: Belang van een goed verzorgd en gecontroleerd corpus...................................................61
Casus 2: Vergelijking en voorspelling van twee tekstuele ‘genres’...................................................62
, Deel 1 – Handmatige tekstanalyse
HOORCOLLEGE 1 - TEKSTANALYSE
Cursusdoelen:
Theoretische concepten beschrijven die ten grondslag liggen aan verschillende
analysemethoden.
De analysemethoden uitleggen in termen van de onderliggende theoretische concepten.
Diverse soorten professionele teksten handmatig/computationeel analyseren, evalueren en -
waar nodig – verbeteren.
Sterke en zwakke aspecten identificeren van handmatige tekstanalyse en van computationele
tekstanalyse.
Gegeven een onderzoeksvraag, een beargumenteerde keuze maken tussen handmatige
tekstanalyse en computationele tekstanalyse.
ANALYSE
Analyse = Een systematisch onderzoek waarbij een probleem ontleed wordt. Alle elementen waaruit
dit probleem bestaat moeten in een analyse worden beschreven en uiteengezet.
Kunnen plaatsvinden op alle mogelijke niveaus, binnen elke denkbare discipline.
‘Probleem’ in deze context verwijst daarom naar: Alle mogelijke situaties die om nader
onderzoek vragen.
- Centraal bij een analyse staat altijd het opdelen van het ‘probleem’ in kleinere elementen,
die gezamenlijk het probleem vormen. Deze kunnen vervolgens afzonderlijk en in relatie
tot elkaar worden onderzocht.
Het onderwerp van zo’n situatie kan concreet of abstract zijn.
- Analyses van concrete problemen zijn bijvoorbeeld genees- en scheikundige analyses.
VB: Analyseren van het menselijk lichaam of het ontleden van stoffen
- Analyses van meer abstracte problemen zijn communicatieanalyses (onderzoek naar
miscommunicatie) of psychoanalyses.
Je kunt één en dezelfde stof/problemen met verschillende oogmerken analyseren, welke
bestanddelen van de stof/probleem relevant zijn voor de analyse is dan ook verschillend.
Oogmerken tekstanalyse:
Tekstkwaliteit (samenhang, schoonheid, amusement) Gegeven een bepaald publiek,
Begrijpelijkheid gegeven een bepaalde context
Doelmatigheid
Tekst samenvatten
Identificatie spam
Idiocyncrasie: Herkenning schrijver
…
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller nienkebreugelmans. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $6.42. You're not tied to anything after your purchase.
Can Stuvia be trusted?
4.6 stars on Google & Trustpilot (+1000 reviews)
53340 documents were sold in the last 30 days
Founded in 2010, the go-to place to buy study notes for 14 years now