Untitled

Abstract

When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning polarities to words in a sentiment lexicon, annotators may use binary, categorical, or continuous labels. Naturally, it is of interest to unify these labels from disparate scales to both achieve maximal coverage over words and to create a single, more robust sentiment lexicon while retaining scale coherence. We introduce a generative model of sentiment lexica to combine disparate scales into a common latent representation. We realize this model with a novel multi-view variational autoencoder (VAE), called SentiVAE. We evaluate our approach via a downstream text classification task involving nine English-Language sentiment analysis datasets; our representation outperforms six individual sentiment lexica, as well as a straightforward combination thereof.

Sentiment as an Ordinal Latent Variable

“…6). For predicting the sentiment labels of documents, we choose a simple procedure following Go et al (2009); Kiritchenko et al (2014); Ozdemir and Bergler (2015); Hoyle et al (2019): for each document, we replace each token with its corresponding sentiment value from a dictionary. Then, we average all values per document and pass it to a logistic regression (LR) model that is fitted on the training set to predict document labels.…”

“…Sentiment analysis is being applied in various domains from political science (Young and Soroka, 2012;Gründl, 2020;Widmann and Wich, 2022) to economics (Stephany et al, 2022) and computational social science (West et al, 2014;Falck et al, 2020;Stoehr et al, 2021). In all of these applications, there is a strong demand for domain-specific and interpretable methods (Hofman et al, 2021;Widmann and Wich, 2022) making dictionarybased sentiment analysis still a popular choice (Young and Soroka, 2012;Hoyle et al, 2019;Gründl, 2020;Friedrichs et al, 2022).…”

Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models

“…Following Hoyle et al (2019a), we use sentiment as a proxy to quantify bias, which requires a sentiment lexicon for each analyzed language. We use the combined sentiment lexicon of Hoyle et al (2019b) for English words, which was shown to outperform a number of individual sentiment lexica and their straight-forward combination on a text classification task involving sentiment analysis. Unfortunately, this is only available for English.…”

“…For the remaining six languages we use Senti-VAE (Hoyle et al, 2019b) -a multi-view variational autoencoder -to combine existing sentiment lexica, the same method Hoyle et al (2019a) use to generate the English sentiment lexicon. Particularly, SentiVAE combines lexica with disparate scales into a common latent representation, where the output represents the strength of each word's sentiment (positive, negative and neutral) in the form of a three-dimensional Dirichlet distribution.…”

“…For Hindi, we combine the sentiment lexica from Chen and Skiena (2014), Desai (2016) and Sharan (2016). 5 Following Hoyle et al (2019b) we evaluate the resulting lexica in a text classification task on a selected dataset for each of the languages. Namely, we use the resulting lexica to automatically label instances with their sentiment, based on the average sentiment of words in each sentence.…”