Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Carrot and Stick: Inducing Self-Motivation with Positive & Negative Feedback

Jimin Sohn, Jeihee Cho, Junyong Lee, Songmu Heo, Ji-Eun Han, David R. Mortensen

TL;DR

To facilitate self-motivation, CArrot and STICk (CASTIC) dataset is proposed, consisting of 12,590 sentences with 5 different strategies for enhancing self-motivation.

Abstract

Positive thinking is thought to be an important component of self-motivation in various practical fields such as education and the workplace. Previous work, including sentiment transfer and positive reframing, has focused on the positive side of language. However, self-motivation that drives people to reach their goals has not yet been studied from a computational perspective. Moreover, negative feedback has not yet been explored, even though positive and negative feedback are both necessary to grow self-motivation. To facilitate self-motivation, we propose CArrot and STICk (CASTIC) dataset, consisting of 12,590 sentences with 5 different strategies for enhancing self-motivation. Our data and code are publicly available at here.

Carrot and Stick: Inducing Self-Motivation with Positive & Negative Feedback

TL;DR

To facilitate self-motivation, CArrot and STICk (CASTIC) dataset is proposed, consisting of 12,590 sentences with 5 different strategies for enhancing self-motivation.

Abstract

Positive thinking is thought to be an important component of self-motivation in various practical fields such as education and the workplace. Previous work, including sentiment transfer and positive reframing, has focused on the positive side of language. However, self-motivation that drives people to reach their goals has not yet been studied from a computational perspective. Moreover, negative feedback has not yet been explored, even though positive and negative feedback are both necessary to grow self-motivation. To facilitate self-motivation, we propose CArrot and STICk (CASTIC) dataset, consisting of 12,590 sentences with 5 different strategies for enhancing self-motivation. Our data and code are publicly available at here.
Paper Structure (27 sections, 2 equations, 8 figures, 7 tables)

This paper contains 27 sections, 2 equations, 8 figures, 7 tables.

Table of Contents

  1. Introduction
  2. CASTIC Dataset
  3. Data Collection
  4. Input sentence
  5. Obstacle and TODO Extraction Module
  6. Obstacle Type and Severity Score
  7. Feedback Generation
  8. Data Distribution
  9. Self-Motivation Framework
  10. Task Formulation
  11. Evaluation
  12. Experimental Setup
  13. Evaluation Metric
  14. Experimental Result
  15. Overall Result
  16. ...and 12 more sections

Figures (8)

  • Figure 1: An example of positive reframing ziems-etal-2022-inducing and feedback generated using our CASTIC framework.
  • Figure 2: Overall procedure of generating CASTIC dataset
  • Figure 3: Prompt for Obstacle and TODO extraction
  • Figure 4: Prompt for Generating Feedback
  • Figure 5: Prompt for evaluating motivation with LLM
  • ...and 3 more figures