Causal graph extraction from news: a comparative study of time-series causality learning techniques
Causal graph extraction from news has the potential to aid in the understanding of complex scenarios. In particular, it can help explain and predict events, as well as conjecture about possible cause-effect connections. However, limited work has addressed the problem of large-scale extraction of cau...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2022-08-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1066.pdf |
| _version_ | 1818489645920419840 |
|---|---|
| author | Mariano Maisonnave Fernando Delbianco Fernando Tohme Evangelos Milios Ana G. Maguitman |
| author_facet | Mariano Maisonnave Fernando Delbianco Fernando Tohme Evangelos Milios Ana G. Maguitman |
| author_sort | Mariano Maisonnave |
| collection | DOAJ |
| description | Causal graph extraction from news has the potential to aid in the understanding of complex scenarios. In particular, it can help explain and predict events, as well as conjecture about possible cause-effect connections. However, limited work has addressed the problem of large-scale extraction of causal graphs from news articles. This article presents a novel framework for extracting causal graphs from digital text media. The framework relies on topic-relevant variables representing terms and ongoing events that are selected from a domain under analysis by applying specially developed information retrieval and natural language processing methods. Events are represented as event-phrase embeddings, which make it possible to group similar events into semantically cohesive clusters. A time series of the selected variables is given as input to a causal structure learning techniques to learn a causal graph associated with the topic that is being examined. The complete framework is applied to the New York Times dataset, which covers news for a period of 246 months (roughly 20 years), and is illustrated through a case study. An initial evaluation based on synthetic data is carried out to gain insight into the most effective time-series causality learning techniques. This evaluation comprises a systematic analysis of nine state-of-the-art causal structure learning techniques and two novel ensemble methods derived from the most effective techniques. Subsequently, the complete framework based on the most promising causal structure learning technique is evaluated with domain experts in a real-world scenario through the use of the presented case study. The proposed analysis offers valuable insights into the problems of identifying topic-relevant variables from large volumes of news and learning causal graphs from time series. |
| first_indexed | 2024-12-10T17:06:30Z |
| format | Article |
| id | doaj.art-433ddaee4e9a4f7babefac5aea789ec3 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-10T17:06:30Z |
| publishDate | 2022-08-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-433ddaee4e9a4f7babefac5aea789ec32022-12-22T01:40:26ZengPeerJ Inc.PeerJ Computer Science2376-59922022-08-018e106610.7717/peerj-cs.1066Causal graph extraction from news: a comparative study of time-series causality learning techniquesMariano Maisonnave0Fernando Delbianco1Fernando Tohme2Evangelos Milios3Ana G. Maguitman4Departamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur, Bahía Blanca, Buenos Aires, ArgentinaInstituto de Matemática de Bahía Blanca, Bahía Blanca, Buenos Aires, ArgentinaInstituto de Matemática de Bahía Blanca, Bahía Blanca, Buenos Aires, ArgentinaFaculty of Computer Science, Dalhousie University, Halifax, CanadaDepartamento de Ciencias e Ingeniería de la Computación, Universidad Nacional del Sur, Bahía Blanca, Buenos Aires, ArgentinaCausal graph extraction from news has the potential to aid in the understanding of complex scenarios. In particular, it can help explain and predict events, as well as conjecture about possible cause-effect connections. However, limited work has addressed the problem of large-scale extraction of causal graphs from news articles. This article presents a novel framework for extracting causal graphs from digital text media. The framework relies on topic-relevant variables representing terms and ongoing events that are selected from a domain under analysis by applying specially developed information retrieval and natural language processing methods. Events are represented as event-phrase embeddings, which make it possible to group similar events into semantically cohesive clusters. A time series of the selected variables is given as input to a causal structure learning techniques to learn a causal graph associated with the topic that is being examined. The complete framework is applied to the New York Times dataset, which covers news for a period of 246 months (roughly 20 years), and is illustrated through a case study. An initial evaluation based on synthetic data is carried out to gain insight into the most effective time-series causality learning techniques. This evaluation comprises a systematic analysis of nine state-of-the-art causal structure learning techniques and two novel ensemble methods derived from the most effective techniques. Subsequently, the complete framework based on the most promising causal structure learning technique is evaluated with domain experts in a real-world scenario through the use of the presented case study. The proposed analysis offers valuable insights into the problems of identifying topic-relevant variables from large volumes of news and learning causal graphs from time series.https://peerj.com/articles/cs-1066.pdfDigital text mediaCausal graph extractionVariable extractionTime-series causality learningInformation extraction from news |
| spellingShingle | Mariano Maisonnave Fernando Delbianco Fernando Tohme Evangelos Milios Ana G. Maguitman Causal graph extraction from news: a comparative study of time-series causality learning techniques PeerJ Computer Science Digital text media Causal graph extraction Variable extraction Time-series causality learning Information extraction from news |
| title | Causal graph extraction from news: a comparative study of time-series causality learning techniques |
| title_full | Causal graph extraction from news: a comparative study of time-series causality learning techniques |
| title_fullStr | Causal graph extraction from news: a comparative study of time-series causality learning techniques |
| title_full_unstemmed | Causal graph extraction from news: a comparative study of time-series causality learning techniques |
| title_short | Causal graph extraction from news: a comparative study of time-series causality learning techniques |
| title_sort | causal graph extraction from news a comparative study of time series causality learning techniques |
| topic | Digital text media Causal graph extraction Variable extraction Time-series causality learning Information extraction from news |
| url | https://peerj.com/articles/cs-1066.pdf |
| work_keys_str_mv | AT marianomaisonnave causalgraphextractionfromnewsacomparativestudyoftimeseriescausalitylearningtechniques AT fernandodelbianco causalgraphextractionfromnewsacomparativestudyoftimeseriescausalitylearningtechniques AT fernandotohme causalgraphextractionfromnewsacomparativestudyoftimeseriescausalitylearningtechniques AT evangelosmilios causalgraphextractionfromnewsacomparativestudyoftimeseriescausalitylearningtechniques AT anagmaguitman causalgraphextractionfromnewsacomparativestudyoftimeseriescausalitylearningtechniques |