REDAffectiveLM: Leveraging Affect Enriched Embedding and Transformer-based Neural Language Model for Readers' Emotion Detection

TL;DR

This work addresses Readers' Emotion Detection for short-text news by proposing REDAffectiveLM, a dual-network model that fuses context-aware transformer representations (XLNet) with affect-enriched embeddings (emoGloVe) learned via counter-fitting. The architecture jointly leverages affective word representations and contextual signals to predict reader emotion profiles through multi-target regression on three datasets (SemEval-2007, RENh-4k, REN-20k). Empirical results show statistically significant improvements over a wide range of baselines, supported by qualitative and quantitative analyses of affect enrichment via attention mechanisms. The approach advances affective computing in reader-oriented tasks and provides resources (REN-20k and code) to enable further research and practical emotion-aware systems.

Abstract

Technological advancements in web platforms allow people to express and share emotions towards textual write-ups written and shared by others. This brings about different interesting domains for analysis; emotion expressed by the writer and emotion elicited from the readers. In this paper, we propose a novel approach for Readers' Emotion Detection from short-text documents using a deep learning model called REDAffectiveLM. Within state-of-the-art NLP tasks, it is well understood that utilizing context-specific representations from transformer-based pre-trained language models helps achieve improved performance. Within this affective computing task, we explore how incorporating affective information can further enhance performance. Towards this, we leverage context-specific and affect enriched representations by using a transformer-based pre-trained language model in tandem with affect enriched Bi-LSTM+Attention. For empirical evaluation, we procure a new dataset REN-20k, besides using RENh-4k and SemEval-2007. We evaluate the performance of our REDAffectiveLM rigorously across these datasets, against a vast set of state-of-the-art baselines, where our model consistently outperforms baselines and obtains statistically significant results. Our results establish that utilizing affect enriched representation along with context-specific representation within a neural architecture can considerably enhance readers' emotion detection. Since the impact of affect enrichment specifically in readers' emotion detection isn't well explored, we conduct a detailed analysis over affect enriched Bi-LSTM+Attention using qualitative and quantitative model behavior evaluation techniques. We observe that compared to conventional semantic embedding, affect enriched embedding increases ability of the network to effectively identify and assign weightage to key terms responsible for readers' emotion detection.

Figures (3)

• Figure 1: t-SNE visualization of few affective words related to basic emotions RGB]220,103,103Anger, RGB]251,153,252Disgust, RGB]103,191,105Fear, Joy, Sadness, and Surprise
• Figure 2: The proposed readers’ emotion detection system, REDAffectiveLM
• Figure 3: Emotion profile correlations in the datasets