Machine Translation Vs. Multilingual Dictionaries Assessing Two Strategies for the Topic Modeling of Multilingual Text Collections

Abstract

The goal of this paper is to evaluate two methods for the topic modeling of multilingual document collections: (1) machine translation (MT), and (2) the coding of semantic concepts using a multilingual dictionary (MD) prior to topic modeling. We empirically assess the consequences of these approaches based on both a quantitative comparison of models and a qualitative validation of each method's potentials and weaknesses. Our case study uses two text collections (of tweets and news articles) in three languages (English, Hebrew, Arabic), covering the ongoing local conflicts between Israeli authorities, settlers, and Palestinian Bedouins in the West Bank. We find that both methods produce a large share of equivalent topics, especially in the context of fairly homogenous news discourse, yet show limited but systematic differences when applied to highly heterogenous social media discourse. While the MD model delivers a more nuanced picture of conflict-related topics, it misses several more peripheral topics, especially those unrelated to the dictionary's focus, which are picked up by the MT model. Our study is a first step toward instrument validation, indicating that both methods yield valid, comparable results, while method-specific differences remain.

Inflaming public debate: a methodology to determine origin and characteristics of hate speech about sexual and gender diversity on Twitter

“…It is a methodology similar to, but different from, Naive Bayes algorithms, in which hateful phrases are identified, and it is machine learning that searches for the words and relationships between them as a way of training and learning to then be applied to new phrases, as used by Arcila- Calderón et al (2021) in Spanish. While there are methodological advances in multilingual dictionaries (Maier et al, 2022), hate detection in Spanish is still in its infancy and needs further development. -Probabilistic determination of bot behaviour through Kearney's (2018) Tweetbotornot algorithm.…”

Cross-Lingual Classification of Political Texts Using Multilingual Sentence Embeddings

“…Full-text translated documents can then be pre-processed and tokenized into words and phrases ( n -gram tokens) to obtain monolingual BoW representations of originally multilingual documents. 2 This approach has been shown to enable reliable dictionary analysis (Windsor, Cupit, and Windsor 2019), topic modeling (de Vries, Schoonvelde, and Schumacher 2018; Lucas et al 2015; Maier et al 2021; Reber 2019), and supervised text classification (Courtney et al 2020; Lind et al 2021b).…”

Distant Political News Classification: Facilitating Machine Learning Identification of News Topics Across Multilingual Text Corpora

“…To solve this issue, some scholars have focused on other techniques to examine multilingual news content, such as (machine) translation (see e.g., Courtney, Breen, McMenamin, & McNulty, 2020;De Vries et al, 2018;Lind et al, 2021;Maier, Baden, Stoltenberg, De Vries-Kedem, & Waldherr, 2022) or multilingual dictionaries (Maier et al, 2022). They show that such techniques can efficiently and effectively be employed for the classification of multilingual data.…”