Measuring party agendas: A neural topic modeling approach
Jana Bernhard, Hajo Boomgaarden
ECREA 2022, 19 – 22 Oktober 2022
Disclaimer: Please be aware that this study is a work in progress.
To further this research, we would be most interested in feedback
on, and the discussion of our methodological approach.
What is a party agenda?
“the list of issues to which political actors pay attention”
(Walgrave et al., 2008, p. 815)
which issues are on political agendas?
(Soroka, 2002)
• Symbolic agendas
• Substantive political agendas
• Prominent issues
• Sensational issues
• Governmntal issues
21.10.2022 Modeling party agendas: A neural network approach Page 3
What is a party agenda?
“the list of issues to which political actors pay attention”
(Walgrave et al., 2008, p. 815)
which issues are on political agendas?
(Soroka, 2002)
• Symbolic agendas
• Substantive political agendas
• Prominent issues
• Sensational issues
• Governmntal issues
21.10.2022 Modeling party agendas: A neural network approach Page 4
Why use an automated approach to measure party agendas?
• Manual Content analysis is time and labour intensive
• „Past work concentrated on a limited number of political agendas“
(Walgraave et al. 2008, p. 815)
1. (often) limited to one channel
2. (often) limited to few parties
3. (often) limited to short timeframe
21.10.2022 Modeling party agendas: A neural network approach Page 5
Automated text analysis is scalable and repetition is cheap.
21.10.2022 Modeling party agendas: A neural network approach Page 6
• Austrian Parties
(SPOE, OEVP, GRUE, FPOE, NEOS)
• National Level, County Level
and Chairpersons
• 2012 – 2021
• Multiple Channels
◦ Tweets
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
SPOE GRUE NEOS FPOE OEVP
Automated text analysis is scalable and repetition is cheap.
21.10.2022 Modeling party agendas: A neural network approach Page 7
• Austrian Parties
(SPOE, OEVP, GRUE, FPOE, NEOS)
• National Level, County Level
and Chairpersons
• 2012 – 2021
• Multiple Channels
◦ Tweets
◦ Facebook Posts
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
SPOE GRUE NEOS FPOE OEVP
Automated text analysis is scalable and repetition is cheap.
21.10.2022 Modeling party agendas: A neural network approach Page 8
• Austrian Parties
(SPOE, OEVP, GRUE, FPOE, NEOS)
• National Level, County Level
and Chairpersons
• 2012 – 2021
• Multiple Channels
◦ Tweets
◦ Facebook Posts
◦ Parliamentary Speeches
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
SPOE GRUE NEOS FPOE OEVP
Automated text analysis is scalable and repetition is cheap.
21.10.2022 Modeling party agendas: A neural network approach Page 9
• Austrian Parties
(SPOE, OEVP, GRUE, FPOE, NEOS)
• National Level, County Level
and Chairpersons
• 2012 – 2021
• Multiple Channels
◦ Tweets
◦ Facebook Posts
◦ Parliamentary Speeches
◦ Press Releases
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
SPOE GRUE NEOS FPOE OEVP
Automated text analysis is scalable and repetition is cheap.
21.10.2022 Modeling party agendas: A neural network approach Page 10
• Austrian Parties
(SPOE, OEVP, GRUE, FPOE, NEOS)
• National Level, County Level
and Chairpersons
• 2012 – 2021
• Multiple Channels
◦ Tweets
◦ Facebook Posts
◦ Parliamentary Speeches
◦ Press Releases
0
20000
40000
60000
80000
100000
120000
140000
SPOE GRUE NEOS FPOE OEVP
How does this neural topic
model (top2vec) work?
Neural Topic Modeling for Issue Detection?
• Topic Modeling detects Topics
(Angelov, 2022)
◦ A topic is the theme, matter or subject of a text
◦ topics are continuous
◦ each document has its own topic with a value in that continuum
• Topics in Parties Communication can be interpreted as the issues they publicly pay
attention to.
21.10.2022 Modeling party agendas: A neural network approach Page 12
1. We look at one parties communication in different channels.
21.10.2022 Modeling party agendas: A neural network approach Page 13
2. they are ordered by the semantic similarity of their words
(based on pre-trained / self-trained word embeddings).
21.10.2022 Modeling party agendas: A neural network approach Page 14
3. Dense clusters in this semantic space are found and denoted
topics.
21.10.2022 Modeling party agendas: A neural network approach Page 15
T1
T2
T3
T4
T5
T6
T7
4. We interpret these topics by looking at the words that are
closest to them.
21.10.2022 Modeling party agendas: A neural network approach Page 16
T1
T2
T3
T4
T5
T6
T7
How can we use these word
and document lists to
measure party agendas?
1. Explore the found issues (excerpt of 5 largest topics)
21.10.2022 Modeling party agendas: A neural network approach Page 20
Green Party Social Democrats Peoples Party Freedom Party Neoliberal Party
Climate Change
Taxes &
Corruption
Taxes & Budgets
Taxes &
Corruption
Reforms
Climate Crisis EU Policy EU Policy EU Budgets EU Policy
EU Policy Youth Policy
Crisis
Communication
Scandals
Environmental
Policy
Education Policy
Environmental
Policy
Education Policy
Attacks on
Government
Climate Crisis
Human Rights Social Work
Internal Party
Politics
Christianity Corruption
2. See how issues develop over time: Climate Change
21.10.2022 Modeling party agendas: A neural network approach Page 21
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
Nationalrat Press Releases Facebook Tweets
3. See how channels differ over time
21.10.2022 Modeling party agendas: A neural network approach Page 22
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
Nationalrat Press Releases Facebook Tweets
3. See how channels differ over time
21.10.2022 Modeling party agendas: A neural network approach Page 23
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
Nationalrat Press Releases Facebook Tweets
3. See how channels differ over time
21.10.2022 Modeling party agendas: A neural network approach Page 24
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
Nationalrat Press Releases Facebook Tweets
3. See how channels differ over time
21.10.2022 Modeling party agendas: A neural network approach Page 25
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
Nationalrat Press Releases Facebook Tweets
4. Compare issue developments between parties
21.10.2022 Modeling party agendas: A neural network approach Page 26
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
SPOE OEVP GRUE FPOE NEOS
21.10.2022 Modeling party agendas: A neural network approach Page 27
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
GRUE
Nationalrat PressReleases Facebook Tweets
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
OEVP
Nationalrat Press Releases Facebook Twitter
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
SPOE
Nationalrat Press Releases Facebook Twitter
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
NEOS
Nationalrat PressReleases Facebook Twitter
0
500
1000
1500
2000
2500
2012 2013 2014 2015 2016 2017 2018 2019 2020 2021
FPOE
Nationalrat Press Releases Facebook Twitter
4. Compare how issues are talked about.
• Which words are the closes to a specific issue
◦ Mathematical similarity measures (cosine similarity)
◦ Qualitative interpretation
• In a next step:
◦ how words differ between channels
◦ How words differ over time
21.10.2022 Modeling party agendas: A neural network approach Page 28
21.10.2022 Modeling party agendas: A neural network approach Page 29
climate crisis, climate policy,
climate protection, climate
action, climate change,
climate ticket
environmental policy,
environment minister,
environmental issues, climate
policy, environmental
protection, federal
environmental agency
climate crisis, climate policy,
climate protection, climate
action, climate change,
climate strike
environmental policy,
minister of the environment,
energy policy, climate policy,
environmental protection,
environmental spokesman
climate policy, climate
protection, climate change,
environmental policy, climate
goals
Can we use neural topic modeling to measure party agendas?
1. Exploratory issue detection
2. Novel issue definition (continuous)
3. Methodological:
a. No Pre-Processing
b. Full set / no sampling
c. Easy replication and data addition
4. Issues over time
5. Comparison on Word Level
6. (word changes over time)
21.10.2022 Modeling party agendas: A neural network approach Page 30
YES!
Can we use neural topic modeling to measure party agendas?
1. Validate, validate, validate
2. Easier approaches also possible
a. Manual Analysis
b. Dictionary Approaches
c. Clustering Approaches
3. Application of computational models should be
considered in light of its usefulness towards the
research question.
21.10.2022 Modeling party agendas: A neural network approach Page 31
BUT …
Neural Topic Models can be a
fruitful approach to
measuring party agendas,
when validated carefully and
useful to the research
question.

2022ECREA_slideshare.pdf

  • 1.
    Measuring party agendas:A neural topic modeling approach Jana Bernhard, Hajo Boomgaarden ECREA 2022, 19 – 22 Oktober 2022
  • 2.
    Disclaimer: Please beaware that this study is a work in progress. To further this research, we would be most interested in feedback on, and the discussion of our methodological approach.
  • 3.
    What is aparty agenda? “the list of issues to which political actors pay attention” (Walgrave et al., 2008, p. 815) which issues are on political agendas? (Soroka, 2002) • Symbolic agendas • Substantive political agendas • Prominent issues • Sensational issues • Governmntal issues 21.10.2022 Modeling party agendas: A neural network approach Page 3
  • 4.
    What is aparty agenda? “the list of issues to which political actors pay attention” (Walgrave et al., 2008, p. 815) which issues are on political agendas? (Soroka, 2002) • Symbolic agendas • Substantive political agendas • Prominent issues • Sensational issues • Governmntal issues 21.10.2022 Modeling party agendas: A neural network approach Page 4
  • 5.
    Why use anautomated approach to measure party agendas? • Manual Content analysis is time and labour intensive • „Past work concentrated on a limited number of political agendas“ (Walgraave et al. 2008, p. 815) 1. (often) limited to one channel 2. (often) limited to few parties 3. (often) limited to short timeframe 21.10.2022 Modeling party agendas: A neural network approach Page 5
  • 6.
    Automated text analysisis scalable and repetition is cheap. 21.10.2022 Modeling party agendas: A neural network approach Page 6 • Austrian Parties (SPOE, OEVP, GRUE, FPOE, NEOS) • National Level, County Level and Chairpersons • 2012 – 2021 • Multiple Channels ◦ Tweets 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% SPOE GRUE NEOS FPOE OEVP
  • 7.
    Automated text analysisis scalable and repetition is cheap. 21.10.2022 Modeling party agendas: A neural network approach Page 7 • Austrian Parties (SPOE, OEVP, GRUE, FPOE, NEOS) • National Level, County Level and Chairpersons • 2012 – 2021 • Multiple Channels ◦ Tweets ◦ Facebook Posts 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% SPOE GRUE NEOS FPOE OEVP
  • 8.
    Automated text analysisis scalable and repetition is cheap. 21.10.2022 Modeling party agendas: A neural network approach Page 8 • Austrian Parties (SPOE, OEVP, GRUE, FPOE, NEOS) • National Level, County Level and Chairpersons • 2012 – 2021 • Multiple Channels ◦ Tweets ◦ Facebook Posts ◦ Parliamentary Speeches 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% SPOE GRUE NEOS FPOE OEVP
  • 9.
    Automated text analysisis scalable and repetition is cheap. 21.10.2022 Modeling party agendas: A neural network approach Page 9 • Austrian Parties (SPOE, OEVP, GRUE, FPOE, NEOS) • National Level, County Level and Chairpersons • 2012 – 2021 • Multiple Channels ◦ Tweets ◦ Facebook Posts ◦ Parliamentary Speeches ◦ Press Releases 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% SPOE GRUE NEOS FPOE OEVP
  • 10.
    Automated text analysisis scalable and repetition is cheap. 21.10.2022 Modeling party agendas: A neural network approach Page 10 • Austrian Parties (SPOE, OEVP, GRUE, FPOE, NEOS) • National Level, County Level and Chairpersons • 2012 – 2021 • Multiple Channels ◦ Tweets ◦ Facebook Posts ◦ Parliamentary Speeches ◦ Press Releases 0 20000 40000 60000 80000 100000 120000 140000 SPOE GRUE NEOS FPOE OEVP
  • 11.
    How does thisneural topic model (top2vec) work?
  • 12.
    Neural Topic Modelingfor Issue Detection? • Topic Modeling detects Topics (Angelov, 2022) ◦ A topic is the theme, matter or subject of a text ◦ topics are continuous ◦ each document has its own topic with a value in that continuum • Topics in Parties Communication can be interpreted as the issues they publicly pay attention to. 21.10.2022 Modeling party agendas: A neural network approach Page 12
  • 13.
    1. We lookat one parties communication in different channels. 21.10.2022 Modeling party agendas: A neural network approach Page 13
  • 14.
    2. they areordered by the semantic similarity of their words (based on pre-trained / self-trained word embeddings). 21.10.2022 Modeling party agendas: A neural network approach Page 14
  • 15.
    3. Dense clustersin this semantic space are found and denoted topics. 21.10.2022 Modeling party agendas: A neural network approach Page 15 T1 T2 T3 T4 T5 T6 T7
  • 16.
    4. We interpretthese topics by looking at the words that are closest to them. 21.10.2022 Modeling party agendas: A neural network approach Page 16 T1 T2 T3 T4 T5 T6 T7
  • 17.
    How can weuse these word and document lists to measure party agendas?
  • 18.
    1. Explore thefound issues (excerpt of 5 largest topics) 21.10.2022 Modeling party agendas: A neural network approach Page 20 Green Party Social Democrats Peoples Party Freedom Party Neoliberal Party Climate Change Taxes & Corruption Taxes & Budgets Taxes & Corruption Reforms Climate Crisis EU Policy EU Policy EU Budgets EU Policy EU Policy Youth Policy Crisis Communication Scandals Environmental Policy Education Policy Environmental Policy Education Policy Attacks on Government Climate Crisis Human Rights Social Work Internal Party Politics Christianity Corruption
  • 19.
    2. See howissues develop over time: Climate Change 21.10.2022 Modeling party agendas: A neural network approach Page 21 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 Nationalrat Press Releases Facebook Tweets
  • 20.
    3. See howchannels differ over time 21.10.2022 Modeling party agendas: A neural network approach Page 22 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 Nationalrat Press Releases Facebook Tweets
  • 21.
    3. See howchannels differ over time 21.10.2022 Modeling party agendas: A neural network approach Page 23 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 Nationalrat Press Releases Facebook Tweets
  • 22.
    3. See howchannels differ over time 21.10.2022 Modeling party agendas: A neural network approach Page 24 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 Nationalrat Press Releases Facebook Tweets
  • 23.
    3. See howchannels differ over time 21.10.2022 Modeling party agendas: A neural network approach Page 25 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 Nationalrat Press Releases Facebook Tweets
  • 24.
    4. Compare issuedevelopments between parties 21.10.2022 Modeling party agendas: A neural network approach Page 26 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 SPOE OEVP GRUE FPOE NEOS
  • 25.
    21.10.2022 Modeling partyagendas: A neural network approach Page 27 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 GRUE Nationalrat PressReleases Facebook Tweets 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 OEVP Nationalrat Press Releases Facebook Twitter 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 SPOE Nationalrat Press Releases Facebook Twitter 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 NEOS Nationalrat PressReleases Facebook Twitter 0 500 1000 1500 2000 2500 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 FPOE Nationalrat Press Releases Facebook Twitter
  • 26.
    4. Compare howissues are talked about. • Which words are the closes to a specific issue ◦ Mathematical similarity measures (cosine similarity) ◦ Qualitative interpretation • In a next step: ◦ how words differ between channels ◦ How words differ over time 21.10.2022 Modeling party agendas: A neural network approach Page 28
  • 27.
    21.10.2022 Modeling partyagendas: A neural network approach Page 29 climate crisis, climate policy, climate protection, climate action, climate change, climate ticket environmental policy, environment minister, environmental issues, climate policy, environmental protection, federal environmental agency climate crisis, climate policy, climate protection, climate action, climate change, climate strike environmental policy, minister of the environment, energy policy, climate policy, environmental protection, environmental spokesman climate policy, climate protection, climate change, environmental policy, climate goals
  • 28.
    Can we useneural topic modeling to measure party agendas? 1. Exploratory issue detection 2. Novel issue definition (continuous) 3. Methodological: a. No Pre-Processing b. Full set / no sampling c. Easy replication and data addition 4. Issues over time 5. Comparison on Word Level 6. (word changes over time) 21.10.2022 Modeling party agendas: A neural network approach Page 30 YES!
  • 29.
    Can we useneural topic modeling to measure party agendas? 1. Validate, validate, validate 2. Easier approaches also possible a. Manual Analysis b. Dictionary Approaches c. Clustering Approaches 3. Application of computational models should be considered in light of its usefulness towards the research question. 21.10.2022 Modeling party agendas: A neural network approach Page 31 BUT …
  • 30.
    Neural Topic Modelscan be a fruitful approach to measuring party agendas, when validated carefully and useful to the research question.