Mohammad H. Forouhesh
Metodata Inc ®
April 25, 2022
A Persian Reimplementation of Prof. Eliot Ash's Framework, Relatio
E. Ash, et al. Text Semantics Capture Political and Economic Narratives
- A Brief Overview
- Main Problem
- Illustrative Example
- I/O
- Motivation
- Related Works
- Contributions of this paper
- Proposed Method
- Experiments
> بازار کریپتو ---هدر داد---> وقت و پول من را
- Input: Tweets (textual modality)
- Output: Predicted salient narratives around historical events.
-
The articulation of partisan values can be discovered by arranging narratives by relative party usage.
-
Narratives provide a new window on polarisation of language in politics.
-
Analysing narratives quantitatively is still largely unexplored.
-
Narrative statements are intuitive and close to the original raw text.
-
Various narratives can form a broader discourse.
According to the dependency parser method, it is divided into 3 categories:
- Dictionary methods rely on matching particular words or phrases Baker, Bloom and Davis, 2016; Shiller, 2019; Enke, 2020
- Unsupervised learning methods such as topic models and document embeddings break sentences down into words or phrases and ignore grammatical information Hansen, McMahon and Prat, 2017; Larsen and Thorsrud, 2019; Bybee et al., 2020.
- syntactic dependency parsers, which identify grammatical relationships between words Ash et al., 2020, will often miss how actors are related in a sentence.
- Multigraph approach that links up entities and their associated actions through a network.
- Robustness to word ordering.
- Giving qualitative researchers a rich context.
- This method can provide insights into narrative discourse and polarisation through node centrality and graph distance measures.
Given a sentence, using Semantic Role Labelling, subject (agent or who), action (verb or what) and target (patient or whom) of the sentence is extracted. A0, V, and A1 are the corresponding set of phrases. Define the set of all narratives N ⊂ A0 ⨉ V ⨉ A1 = S. This set can be too high-dimensional.
Construct the set E of latent entities such that: (not for verbs)
-
|E| < |A0 U A1 |
-
N = E ⨉ V ⨉ E
If an entity is frequent, then it is explicit, otherwise, it is implicit. Sometimes, a sentence entity has no surface form, this is also categorised under the umbrella term of implicit entity.
- Explicit: Apply Named Entity Recognition, then chose top L frequent entities.
- Implicit: Embed sentence then apply K-Means, each cluster represents a latent entity.
Find the narrative representation of each sentence, create complex narratives by combination. These complex narratives can be analysed using the degree of input and output.
U.S. Congressional Record, 1994-2015. Transcripts of speeches made in the House and Senate with names and party affiliations. Often used as a data source for text analysis in social science applications.
L = 1000 K = 1000
In short narratives capture the following:
- Historical Events: e.g. Sep 11, war on terror
- Sentiment Polarity
- Partisanship
- Debate Structure
A sample from the output: