Exploring the Political Agenda of the Greek Parliament Plenary Sessions

Size: px

Start display at page:

Download "Exploring the Political Agenda of the Greek Parliament Plenary Sessions"

Hilary Ray
5 years ago
Views:

1 Exploring the Political Agenda of the Greek Parliament Plenary Sessions Dimitris Gkoumas, Maria Pontiki, Konstantina Papanikolaou, and Haris Papageorgiou ATHENA Research & Innovation Centre/Institute for Language & Speech Processing (ATHENA RIC/ILSP), Greece. Computational Science and Technologies: Data, Content and Interaction (MIS ) APOLLONIS, Greek Infrastructure for Digital Arts and Humanities, Language Research and Innovation (MIS ) 7 May 2018, Miyazaki, Japan

2 Parliament plenary sessions: Valuable Data Sources Capturing the way political and policy agendas are shaped and evolve over time. Reflecting the stance and the political behavior under which individual Parliament Members and political groups react and actover time. 2/20

Parliament plenary sessions & Topic Modelling Insights about: the way in which the European Parliament reacts to exogenous events like the Eurocrisis (Greene and Gross, 2017) the political attention

3 Parliament plenary sessions & Topic Modelling Insights about: the way in which the European Parliament reacts to exogenous events like the Eurocrisis (Greene and Gross, 2017) the political attention of individual U.S. Senators (Quinn et al., 2010) Image source: 3/20

4 Exploring the Political Agenda of the Greek Parliament Plenary Sessions Methodology: Overview Data Collection Data Preparation Preprocessing Organization Topic Modelling Visualization 4/20

5 Data Collection Data Preparation Preprocessing Organization Topic Modelling Visualization Data Collection 1989 to 2015 proceedings à4356 plenary sessions à unique speeches 5/20

6 Data Preparation Data Collection Preprocessing Organization Topic Modelling Visualization Data Preparation Different formats (txt/doc/docx/pdf/jpeg) à structured and machine-readable xml version 6/20

Preprocessing Data Collection Data Preparation Organization Topic Modelling Visualization Preprocessing ü Segment annotation: the start/end point of each

7 Preprocessing Data Collection Data Preparation Organization Topic Modelling Visualization Preprocessing ü Segment annotation: the start/end point of each speech ü Temporal annotation: the date of each speech ü Speaker annotation: the name of each speaker and his/her political affiliation ü POS tagging 7/20

8 Data Organization Data Collection Data Preparation Preprocessing Topic Modelling Visualization Organization ü time windows of fixed durationà 1 month ü 283 windows for the time period from 1989 to 2015 àdiscover topics within the monthly proceedings (e.g. segments) & monitor their dynamics over time 8/20

9 Topic Modelling Data Collection Data Preparation Preprocessing Organization Visualization Topic Modelling q Dynamic Non-negative Matrix Factorization (NMF) approach (Greene and Cross, 2017). q After identifying a certain number of topics in each 1-month-window, the ones which are semantically similar are grouped together as dynamic topics, rather than identifying topics from the beginning. 9/20

Dynamic NMF Phase 1 Document term-matrix TF-IDF normalized -stop words, +content words -rare terms & units with length less than three lines, +nouns & adjectives NMF model generates topics for each

10 Dynamic NMF Phase 1 Document term-matrix TF-IDF normalized -stop words, +content words -rare terms & units with length less than three lines, +nouns & adjectives NMF model generates topics for each window Input Processed and organized data 283 monthly windows, unique speeches Phase 2 NMF algorithm is applied again, with the number of k topics decided after applying the Topic Coherence via Word2Vec (TC-W2V) GrParl speeches used as a training corpus for the extraction of the word embeddings Output 283 windowbased topics 90 dynamic topics 10/20

11 Visualization Data Collection Data Preparation Preprocessing Organization Topic Modelling Visualization ü By topic ü By time ü Search function 11/20

12 Greek Parliament Plenary Sessions presented by topic 12/20

13 20 most prominent words for the dynamic topic D79 13/20

14 Involved Parliament Members 14/20

15 Contribution of each political party to a dynamic topic 15/20

16 Contribution of each region to a dynamic topic 16/20

17 Most important window-topics related to a dynamic topic 17/20

18 Greek Parliament Plenary Sessions presented by time 18/20

19 Discussion Contributio n Transformation of the Greek Parliament plenary sessions minutes into a structured and machine readable corpus Insightful navigation across the Greek Parliament corpus For the first time available for Natural Language Processing and Text Mining approaches Topic based presentation Time-window based presentation Search function Future Work Qualitative analysis of the extracted dynamic topics & assignment of descriptive labels Exploration of the evolution of selected topics (e.g. refugee crisis, Eurocrisis) & comparison with the European Parliament and/or other European countries Enrichment with more insights e.g. Quotations, Sentiment 19/20

20 Exploring the Political Agenda of the Greek Parliament Plenary Sessions Dimitris Gkoumas, Maria Pontiki, Konstantina Papanikolaou, and Haris Papageorgiou ATHENA-Research & Innovation Centre in Information, Communication and Knowledge Technologies (ATHENA RIC), Greece. Computational Science and Technologies: Data, Content and Interaction (MIS ) APOLLONIS, Greek Infrastructure for Digital Arts and Humanities, Language Research and Innovation (MIS ) 7 May 2018, Miyazaki, Japan

Document Content-Based Search Using Topic Modeling

Document Content-Based Search Using Topic Modeling Jason Bello, Brian de Silva, Jerry Luo University of California, Los Angeles August 9, 2013 Jason Bello, Brian de Silva, Jerry Luo (UCLA) Topic Modeling