# Affect-LM: A Neural Language Model for Customizable Affective Text Generation

arXiv: https://arxiv.org/abs/1704.06851 · HTML: https://mlsanity.com/paper/1704.06851/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2017.

## Built on by (most cited first, 30 of 50)

- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [Building Emotional Support Chatbots in the Era of LLMs](https://mlsanity.com/paper/2308.11584/) (2023)
- [Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder](https://mlsanity.com/paper/2304.04052/) (2023)
- [Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought](https://mlsanity.com/paper/2401.06836/) (2024)
- [Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction](https://mlsanity.com/paper/2106.03044/) (2021)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges](https://mlsanity.com/paper/2405.15604/) (2024)
- [EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention](https://mlsanity.com/paper/2210.12463/) (2022)
- [C5T5: Controllable Generation of Organic Molecules with Transformers](https://mlsanity.com/paper/2108.10307/) (2021)
- [An End-to-End Network for Emotion-Cause Pair Extraction](https://mlsanity.com/paper/2103.01544/) (2021)
- [Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation](https://mlsanity.com/paper/2301.04907/) (2023)
- [ENTRUST: Argument Reframing with Language Models and Entailment](https://mlsanity.com/paper/2103.06758/) (2021)
- [EmpHi: Generating Empathetic Responses with Human-like Intents](https://mlsanity.com/paper/2204.12191/) (2022)
- [MOPO: Multi-Objective Prompt Optimization for Affective Text Generation](https://mlsanity.com/paper/2412.12948/) (2024)
- [Affective Computing Has Changed: The Foundation Model Disruption](https://mlsanity.com/paper/2409.08907/) (2024)
- [Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text](https://mlsanity.com/paper/2112.00800/) (2021)
- [CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions](https://mlsanity.com/paper/2210.05221/) (2022)
- [Emotion-Conditioned Text Generation through Automatic Prompt Optimization](https://mlsanity.com/paper/2308.04857/) (2023)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [Detoxifying Language Models with a Toxic Corpus](https://mlsanity.com/paper/2205.00320/) (2022)
- [Plug-and-Play Recipe Generation with Content Planning](https://mlsanity.com/paper/2212.05093/) (2022)
- [A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots](https://mlsanity.com/paper/2401.00609/) (2023)
- [Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition](https://mlsanity.com/paper/2402.17269/) (2024)
- [Affective Decoding for Empathetic Response Generation](https://mlsanity.com/paper/2108.08102/) (2021)
- [Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Training](https://mlsanity.com/paper/2111.06181/) (2021)
- [Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing Generation](https://mlsanity.com/paper/2210.16557/) (2022)
- [Affective Natural Language Generation of Event Descriptions through Fine-grained Appraisal Conditions](https://mlsanity.com/paper/2307.14004/) (2023)
- [A Review of Affective Generation Models](https://mlsanity.com/paper/2202.10763/) (2022)

## Abstract (arXiv)

Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generating conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM generates naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affect-discriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.