Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sentiment and Emotion-aware Multi-criteria Fuzzy Group Decision Making System

Adilet Yerkin, Pakizar Shamoi, Elnara Kadyrgali

TL;DR

This paper addresses the gap in group decision-making by enabling participants to express opinions in natural language and emotional tone. It introduces a sentiment- and emotion-aware multi-criteria fuzzy GDM framework that fuses NLP-derived signals with a fuzzy inference system to produce a total preference for each alternative, demonstrated on a hotel-selection task. The approach combines voting data with qualitative sentiment and emotional cues, yielding higher consensus as measured by consensus metrics, and demonstrates the practical value of incorporating affective information into GDM. This framework offers a scalable, emotion-informed method for real-world group decisions and sets the stage for comparisons with traditional multi-criteria methods and larger-scale evaluations.

Abstract

In today's world, making decisions as a group is common, whether choosing a restaurant or deciding on a holiday destination. Group decision-making (GDM) systems play a crucial role by facilitating consensus among participants with diverse preferences. Discussions are one of the main tools people use to make decisions. When people discuss alternatives, they use natural language to express their opinions. Traditional GDM systems generally require participants to provide explicit opinion values to the system. However, in real-life scenarios, participants often express their opinions through some text (e.g., in comments, social media, messengers, etc.). This paper introduces a sentiment and emotion-aware multi-criteria fuzzy GDM system designed to enhance consensus-reaching effectiveness in group settings. This system incorporates natural language processing to analyze sentiments and emotions expressed in textual data, enabling an understanding of participant opinions besides the explicit numerical preference inputs. Once all the experts have provided their preferences for the alternatives, the individual preferences are aggregated into a single collective preference matrix. This matrix represents the collective expert opinion regarding the other options. Then, sentiments, emotions, and preference scores are inputted into a fuzzy inference system to get the overall score. The proposed system was used for a small decision-making process - choosing the hotel for a vacation by a group of friends. Our findings demonstrate that integrating sentiment and emotion analysis into GDM systems allows everyone's feelings and opinions to be considered during discussions and significantly improves consensus among participants.

Sentiment and Emotion-aware Multi-criteria Fuzzy Group Decision Making System

TL;DR

This paper addresses the gap in group decision-making by enabling participants to express opinions in natural language and emotional tone. It introduces a sentiment- and emotion-aware multi-criteria fuzzy GDM framework that fuses NLP-derived signals with a fuzzy inference system to produce a total preference for each alternative, demonstrated on a hotel-selection task. The approach combines voting data with qualitative sentiment and emotional cues, yielding higher consensus as measured by consensus metrics, and demonstrates the practical value of incorporating affective information into GDM. This framework offers a scalable, emotion-informed method for real-world group decisions and sets the stage for comparisons with traditional multi-criteria methods and larger-scale evaluations.

Abstract

In today's world, making decisions as a group is common, whether choosing a restaurant or deciding on a holiday destination. Group decision-making (GDM) systems play a crucial role by facilitating consensus among participants with diverse preferences. Discussions are one of the main tools people use to make decisions. When people discuss alternatives, they use natural language to express their opinions. Traditional GDM systems generally require participants to provide explicit opinion values to the system. However, in real-life scenarios, participants often express their opinions through some text (e.g., in comments, social media, messengers, etc.). This paper introduces a sentiment and emotion-aware multi-criteria fuzzy GDM system designed to enhance consensus-reaching effectiveness in group settings. This system incorporates natural language processing to analyze sentiments and emotions expressed in textual data, enabling an understanding of participant opinions besides the explicit numerical preference inputs. Once all the experts have provided their preferences for the alternatives, the individual preferences are aggregated into a single collective preference matrix. This matrix represents the collective expert opinion regarding the other options. Then, sentiments, emotions, and preference scores are inputted into a fuzzy inference system to get the overall score. The proposed system was used for a small decision-making process - choosing the hotel for a vacation by a group of friends. Our findings demonstrate that integrating sentiment and emotion analysis into GDM systems allows everyone's feelings and opinions to be considered during discussions and significantly improves consensus among participants.
Paper Structure (10 sections, 2 equations, 5 figures, 10 tables)

This paper contains 10 sections, 2 equations, 5 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Fuzzy Approach in Decision Making
  4. Sentiment and Emotion Analysis for Decision Making
  5. Methodology
  6. Preferences, voting system
  7. Sentiment analysis
  8. Fuzzy Inference System
  9. Experiment and Results
  10. Conclusion

Figures (5)

  • Figure 1: Sentiment and Emotion-aware Multi-criteria Fuzzy Group Decision Making System
  • Figure 2: Input and Output Fuzzy Sets of preference scores
  • Figure 3: 3D graphic representations of a set of possible fuzzy system solutions
  • Figure 4: Fuzzy Inference system preferences
  • Figure 5: Visual representation of the inference process. For example, the Agreement value is 8.8, and the Confidence value is 3.4. As a result, we get a Feedback value$\approx$ 6.94.