Table of Contents
Fetching ...

Mapping the Technological Future: A Topic, Sentiment, and Emotion Analysis in Social Media Discourse

Alina Landowska, Maciej Skorski, Krzysztof Rajda

TL;DR

This study investigates how social media discourses encode anticipated technological futures and the emotions surrounding them. It combines BERTopic topic modeling with sentiment and emotion analysis on 1.5 million tweets from 2021–2023 and 400 KOLs to map futures-in-the-making and quantify anticipatory emotions, revealing a predominance of positive sentiment and Hope over Anxiety. By formalizing optimism and pessimism through relationships with Anticipation, Trust, Joy, and Sadness, the work demonstrates how a small set of influencers shape discourse across multiple technology domains and time, with notable event-driven spikes around major gatherings. The integration of contextual topic structure, non-contextual keyword analysis, and affective measurements offers a scalable framework for forecasting and scenario planning, while highlighting limitations related to sample bias and scope to Twitter data. Practical implications include enhancing AI simulations of future discourse and informing strategies for inclusive, nuanced public communication about emerging technologies. Future work should extend to other media sources, longitudinal tracking, and refined models to better capture optimism and risk signals in anticipatory discourse.

Abstract

People worldwide are currently confronted with a number of technological challenges, which act as a potent source of uncertainty. The uncertainty arising from the volatility and unpredictability of technology (such as AI) and its potential consequences is widely discussed on social media. This study uses BERTopic modelling along with sentiment and emotion analysis on 1.5 million tweets from 2021 to 2023 to identify anticipated tech-driven futures and capture the emotions communicated by 400 key opinion leaders (KOLs). Findings indicate positive sentiment significantly outweighs negative, with a prevailing dominance of positive anticipatory emotions. Specifically, the 'Hope' score is approximately 10.33\% higher than the median 'Anxiety' score. KOLs emphasize 'Optimism' and benefits over 'Pessimism' and challenges. The study emphasizes the important role KOLs play in shaping future visions through anticipatory discourse and emotional tone during times of technological uncertainty.

Mapping the Technological Future: A Topic, Sentiment, and Emotion Analysis in Social Media Discourse

TL;DR

This study investigates how social media discourses encode anticipated technological futures and the emotions surrounding them. It combines BERTopic topic modeling with sentiment and emotion analysis on 1.5 million tweets from 2021–2023 and 400 KOLs to map futures-in-the-making and quantify anticipatory emotions, revealing a predominance of positive sentiment and Hope over Anxiety. By formalizing optimism and pessimism through relationships with Anticipation, Trust, Joy, and Sadness, the work demonstrates how a small set of influencers shape discourse across multiple technology domains and time, with notable event-driven spikes around major gatherings. The integration of contextual topic structure, non-contextual keyword analysis, and affective measurements offers a scalable framework for forecasting and scenario planning, while highlighting limitations related to sample bias and scope to Twitter data. Practical implications include enhancing AI simulations of future discourse and informing strategies for inclusive, nuanced public communication about emerging technologies. Future work should extend to other media sources, longitudinal tracking, and refined models to better capture optimism and risk signals in anticipatory discourse.

Abstract

People worldwide are currently confronted with a number of technological challenges, which act as a potent source of uncertainty. The uncertainty arising from the volatility and unpredictability of technology (such as AI) and its potential consequences is widely discussed on social media. This study uses BERTopic modelling along with sentiment and emotion analysis on 1.5 million tweets from 2021 to 2023 to identify anticipated tech-driven futures and capture the emotions communicated by 400 key opinion leaders (KOLs). Findings indicate positive sentiment significantly outweighs negative, with a prevailing dominance of positive anticipatory emotions. Specifically, the 'Hope' score is approximately 10.33\% higher than the median 'Anxiety' score. KOLs emphasize 'Optimism' and benefits over 'Pessimism' and challenges. The study emphasizes the important role KOLs play in shaping future visions through anticipatory discourse and emotional tone during times of technological uncertainty.
Paper Structure (18 sections, 3 equations, 16 figures, 5 tables)

This paper contains 18 sections, 3 equations, 16 figures, 5 tables.

Figures (16)

  • Figure 1: The Hierarchical Clustering of Anticipated Technology-Driven Futures
  • Figure 2: The Dynamics of Selected Topics Over Time
  • Figure 3: Topic leaders.
  • Figure 4: Number of Tweets by Top-Performing KOLs in the Corpus
  • Figure 5: Contribution Distribution Across Topics in Robotics/Robots Engineering versus VR/AR/Audio Technology
  • ...and 11 more figures