mlsanityData to 7 Oct 2026

SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment

arXiv 1806.05521 ↗First posted 14 Jun 2018cs.CL cs.CYcited by 25

Not on the map. Why?

Abstract (arXiv)

Because word semantics can substantially change across communities and contexts, capturing domain-specific word semantics is an important challenge. Here, we propose SEMAXIS, a simple yet powerful framework to characterize word semantics using many semantic axes in word- vector spaces beyond sentiment. We demonstrate that SEMAXIS can capture nuanced semantic representations in multiple online communities. We also show that, when the sentiment axis is examined, SEMAXIS outperforms the state-of-the-art approaches in building domain-specific sentiment lexicons.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 6; 2024: 6; 2025: 4; 2026: 1.

25 papers.

Sort:

By area:

  1. 2021Uncovering Implicit Gender Bias in Narratives through Commonsense Inferencecited by 32
  2. 2022Discovering Differences in the Representation of People using Contextualized Semantic Axescited by 12
  3. 2021Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured Sparsitycited by 9
  4. 2023SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddingscited by 9
  5. 2024A semantic embedding space based on large language models for modelling human beliefscited by 9
  6. 2024Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddingscited by 6
  7. 2023Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Modelscited by 5
  8. 2024Adjusting Interpretable Dimensions in Embedding Space with Human Judgmentscited by 4
  9. 2024Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddingscited by 3
  10. 2022The Ordered Matrix Dirichlet for State-Space Modelscited by 2
  11. 2025Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representationscited by 2
  12. 2022Unsupervised Detection of Contextualized Embedding Bias with Application to Ideologycited by 1
13 more
  1. 2025Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steeringcited by 1
  2. 2021Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoderscited by 0
  3. 2021Making sense of electrical vehicle discussions using sentiment analysis on closely related news and user commentscited by 0
  4. 2022Using Full-Text Content to Characterize and Identify Best Seller Bookscited by 0
  5. 2023CIDER: Context sensitive sentiment analysis for short-form textcited by 0
  6. 2023Moral consensus and divergence in partisan language usecited by 0
  7. 2023Labor Space: A Unifying Representation of the Labor Market via Large Language Modelscited by 0
  8. 2023Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appealscited by 0
  9. 2024The Language of Weather: Social Media Reactions to Weather Accounting for Climatic and Linguistic Baselinescited by 0
  10. 2024Capturing Differences in Character Representations Between Communities: An Initial Study with Fandomcited by 0
  11. 2025Big Data and the Computational Social Science of Entrepreneurship and Innovationcited by 0
  12. 2025Evaluating Machine Translation Datasets for Low-Web Data Languages: A Gendered Lenscited by 0
  13. 2026STEREODISCO: Discovering Stereotypicality in LLMscited by 0