I’m attending the Symposium on the New Frontiers of Automated Content Analysis in the Social Sciences at the University of Zurich – July 1-3, 2015. I will be presenting a paper on using syntactic analysis for analysing clauses. Abstract is copied below, you can download the full paper and the presentation slides.
Clause analysis: using syntactic information to enrich frequency-based automatic content analysis
Wouter van Atteveldt (VU Amsterdam)
Tamir Sheafer, Shaul Shenhav, Yair Fogel-Dror (Hebrew U. Jerusalem)
This paper shows how syntactic information can be used to automatically
extract clauses from text, consisting of a subject, predicate, and optional
source. Since the output of this analysis can be seen as an enriched token
list or bag of words, normal frequency based or corpus linguistic analyses
can be used on this output. Taking the 2008–2009 Gaza war as an example,
we show how corpus comparison, topic modelling, and semantic network
analysis can be used to explore the differences between US and Chinese
coverage of this war.
Next week (22-26 June) I will give a course on programming and analyzing in R as part of the VU FSW Graduate School.
Time: Monday – Thursday, 9:00 – 13:00, with open lab until 15:30.
Location: HG 10-A41
Course Material: github repository (subject to minor changes)
Preparation: Please bring your own laptop (contact me if you don’t have a laptop) and make sure to have the newest version of R and RStudio installed on your computer. Also please install the devtools and RTextTools packages and use devtools to install the amcat/amcat-r and kasperwelbers/corpustools packages by running the following code in RStudio:
Note: on Windows, devtools might give a warning message, you can just ignore the message. Please contact me if you have any difficulty installing the above!
|Lecure + Hands-on 1
||9:00 – 11:00
||Combining and Transforming Data
||Advanced statistics and language features
||Analysing text with AmCAT and R
|Lecure + Hands-on 2
||11:00 – 13:00
||Your data in R
||Basic statistics and plotting
||Analyzing Text and Networks
||Social and Semantic Network Analysis
||14:00 – 15:30
||Lab – assignment 1
||Lab – assignment 2
||Lab – assignment 3
||Lab – assignment 4
Good books on R:
- “Discovering Statistics using R”, by Field, Miles, and Field (Sage 2012).
- “R for SPSS users” (Robert A. Muenchen, Springer 2009)
- “the R book” (Michael J. Crawley, Wiley 2012).
The course is open to all Ph.D. students and colleagues (from the VU or other Universities) but a fee may apply, please contact me if you wish to attend or audit.
See you Monday!
Woensdag 29 april geef ik een practicum over kwantitatieve inhoudsanalyse voor de bachelor- en premastertheses.
Tijd: Woensdag 29 april, 9:00 – 12:45
Locatie: VU HG-1G23
Downloads: [slides] [handout automatische analyse] [handout handmatige analyse]
Kasper Welbers and I will be giving a workshop on automatic text analysis at the Center for Journalism Studies of the University of Gent on the 15th of April.
Downloads: [slides] [handout Corpus Analysis] [handout LDA] [handout Clause Analysis][R Project with sources]
I’m giving a presentation on using syntactic clauses to analyse conflict coverage for the Analyzing Political Discourse in the International Arena workshop on March 22nd at the Hebrew University, Jerusalem. Download my presentation
In a reaction to the recent unrest at the UvA and earlier at the VU, together with 140 colleages at the VU Faculty of Social Sciences I signed an open letter to the board (CvB) where we express our concerns about the lack of democracy and transparancy, the rise of thinking in terms of management and efficiency, and the increasing number of temporary contracts:
Geacht College van Bestuur van de Vrije Universiteit Amsterdam,
De studentenacties en docentenacties aan de UvA en aan andere universiteiten, volgend op jarenlange onrust van medewerkers en studenten (ook hier op de VU), hebben heel wat losgemaakt en tot een breed maatschappelijk en politiek debat geleid. Wij, stafleden van de Faculteit der Sociale Wetenschappen (FSW) van de Vrije Universiteit Amsterdam, verklaren ons solidair met de roep om een aantal fundamentele veranderingen in de organisatie van academisch onderzoek en onderwijs in Nederland. Wij herkennen veel van de geuite zorgen, met name over het gebrek aan democratie, inspraak en transparantie, de invloed van het doorgeschoten rendementsdenken op onderzoek en onderwijs en het groot aantal tijdelijke en flex-contracten. [lees meer]
Youth crime in the Netherlands has fallen by half for the last decade, but the news coverage has stayed roughly the same. In a Dutch report published in january on behalf of WODC, together with Nel Ruigrok of the Nieuwsmonitor, Sarah Gagestein of Taalstrategie, and others we investigate the amount of coverage of youth crime, which sources are used, and how the topic is framed. It turns out that especially in the popular media and online media attention for youth crime has increased between 2007 and 2011. Government sources have a larger share of voice in 2011, and framing in terms of repression has increased. We conclude that this is mainly caused by journalists following the lead of the ministers Opstelten and “crimefighter” Teeven, who both recently resigned from cabinet.
The report was recently covered by Telegraaf, De Ochtend (NPO Radio 1), Metro, Fok, PowNed, and The Post Online.
Read the full report or the summary (both in Dutch)
I will be giving a workshop/tutorial on using R for automatic information extraction at the EUI. This is part of the Innovations in Quantitative Content Analysis workshop organized by Hanspeter Kriesi, Swen Hutter, and Jasmine Lorenzini.
Date: Thursday, February 26th, 12:30 – 17:30
Location: EUI Florence, Emeroteca, Badia Fiesolana
Materials: Slides, Learning R, handouts on Corpus Analysis and Clause Analysis
At the bottom of this post is an overview of the programme/contents of my tutorial. As the tutorial is interactive and will use R for all of the analyses, please make sure to have the newest version of R and RStudio installed on your computer. Also please install the devtools and RTextTools packages and use devtools to install the amcat/amcat-r and kasperwelbers/corpustools packages by running the following code in RStudio:
If you have any trouble installing R, Rstudio, or these packages, it would be great if you could mail me beforehand so we don’t waste our time in the workshop hunting down installation problems.
||Goals / Topics
||Introduction to R
||- Make sure R/Rstudio/amcatr/rtexttools/corpus-tools is installed and running
– Basics of R: variables, vectors, data frames
– Selecting and transforming data
and the Document-Term matrix
|- Create and play with dtm’s
– Understand tokenizing, stemming, lemmatizing etc.
– Using corpus-tools:
– Word frequency analysis and filtering
– Comparing corpora
– Topic modeling
– Using amcat+amcatr for preproccesing
||- understanding the link between syntax and clauses
– using amcat+amcatr to perform source+clause analysis
– combining clause analysis with keyword analysis
– combining clause analysis with corpus analysis/topic modeling
I am pleased to announce that Leo Kim will present at the VU communication science research colloquium 16 February 15:30, Metropolian Z009 at the VU University Amsterdam.
Leo Kim is currently finalizing his Ph.D. at the University of Sussex and has done extensive research on media monitoring and social and semantic network analysis. He is currently CEO of Treum, a Korean company specialized in (social) media monitoring with customers such as Samsung and Coca Cola.
See e.g: https://www.youtube.com/watch?v=LnVRnnHMvUU and http://thenextweb.com/asia/2012/05/17/koreas-treum-helps-companies-cut-through-the-noise-and-find-value-from-social-media-data/
The challenges of semantic network analysis and its practical applications
The methodology of semantic network analysis has inspired intellectuals in social sciences for its semiotic implications, calculability and powerful visual graphics.
However, the variable and complex nature of data processing, thresholding, and presentation to uninformed public imposed additional challenges to convince its use.
In order to entrench the methodology more stable and communicable, the company Ars Praxia (formerly Treum) has engaged in methodological improvements over a few years. In this presentation, the presenter shares the trajectory of methodological improvements faced with current challenges, and shares cases of practical applications that had lasting social impacts.