Public Perception of the Brain-Computer Interface Based on a Decade of Data on X: Mixed Methods Study

Abstract

Background: Given the recent evolution and achievements in brain-computer interface (BCI) technologies, understanding public perception and sentiments toward such novel technologies is important for guiding their communication strategies in marketing and education.

Objective: This study aims to explore the public perception of BCI technology by examining posts on X (formerly known as Twitter) using natural language processing (NLP) methods.

Methods: A mixed methods study was conducted on BCI-related posts from January 2010 to December 2021. The dataset included 65,340 posts from 38,962 unique users. This dataset was subject to a detailed NLP analysis including VADER, TextBlob, and NRCLex libraries, focusing on quantifying the sentiment (positive, neutral, and negative), the degree of subjectivity, and the range of emotions expressed in the posts. The temporal dynamics of sentiments were examined using the Mann-Kendall trend test to identify significant trends or shifts in public interest over time, based on monthly incidence. We used the Sentiment.ai tool to infer users' demographics by matching predefined attributes in users' profile biographies to certain demographic groups. We used the BERTopic tool for semantic understanding of discussions related to BCI.

Results: The analysis showed a significant rise in BCI discussions in 2017, coinciding with Elon Musk's announcement of Neuralink. Sentiment analysis revealed that 59.38% (38,804/65,340) of posts were neutral, 32.75% (21,404/65,340) were positive, and 7.85% (5132/65,340) were negative. The average polarity score demonstrated a generally positive trend over the course of the study (Mann-Kendall Statistic=0.266; τ=0.266; P<.001). Most posts were objective (50,847/65,340, 77.81%), with a smaller proportion being subjective (14,393/65,340, 22.02%). Biographic analysis showed that the "broadcasting" group contributed the most to BCI discussions (17,803/58,030, 30.67%), while the "scientific" group, contributing 27.58% (n=16,005), had the highest overall engagement metrics. The emotional analysis identified anticipation (score = 10,802/52,618, 20.52%), trust (score=9244/52,618, 17.56%), and fear (score=7344/52,618, 13.95%) as the most prominent emotions in BCI discussions. Key topics included Neuralink and Elon Musk, practical applications of BCIs, and the potential for gamification.

Conclusions: This NLP-assisted study provides a decade-long analysis of public perception of BCI technology based on data from X. Overall, sentiments were neutral yet cautiously apprehensive, with anticipation, trust, and fear as the dominant emotions. The presence of fear underscores the need to address ethical concerns, particularly around data privacy, safety, and transparency. Transparent communication and ethical considerations are essential for building public trust and reducing apprehension. Influential figures and positive clinical outcomes, such as advancements in neuroprosthetics, could enhance favorable perceptions. The gamification of BCI, particularly in gaming and entertainment, also offers potential for wider public engagement and adoption. However, public perceptions on X may differ from other platforms, affecting the broader interpretation of results. Despite these limitations, the findings provide valuable insights for guiding future BCI developments, policy making, and communication strategies.

Keywords: BCI; Mann-Kendall; NLP; Neuralink; Twitter; brain-computer interface; brain-machine interface; data; decade; education; innovation; marketing; mixed method; natural language processing; public perception; public perceptions; semantic; sentiment; sentiment analysis; social media; technology.

Figure 1.. The number of posts shared on X discussing brain-computer interface (BCI) annually from 2010 to 2021. From 2010 to 2014, the number of posts remained relatively steady, fluctuating but less than 4000 per year. A gradual increase began in 2015, peaking sharply in 2017 at around 16,000 posts, marking the highest level of activity in the timeline. This spike coincides with the public announcements of Elon Musk’s BCI company, Neuralink, and Facebook’s BCI project. Following this peak, there was a substantial drop in 2018, with post numbers returning to earlier levels. From 2019 to 2021, the number of posts showed a fluctuating yet gradual increase.

Figure 2.. The number of posts shared on X discussing brain-computer interface (BCI) per month of the year 2017. The number of posts increases from January, peaking in March and April at over 3000 posts each month. The peak in March (a) coincides with Neuralink’s public announcement, while the peak in April (b) aligns with Facebook’s announcement of its BCI project. Following these peaks, there is a sharp decline in May, with the number of posts dropping to the lowest point in June. A slight increase is observed in July, but the number of posts remains lower than the earlier peaks, stabilizing at lower levels from September to December.

Figure 3.. The annual number of brain-computer interface–related posts on X from 2010 to 2021, categorized by sentiment. Positive sentiment posts (green line) increased significantly from 2016, peaking in 2017 at over 3500 posts, followed by a decline in 2018 and subsequent growth through 2021. Negative sentiment posts (red line) remained relatively steady throughout the period, showing minor fluctuations but consistently lower numbers compared to positive sentiment posts. Overall, positive sentiment posts were more prevalent than negative ones across all years.

Figure 4.. The annual trend of primary emotions—trust, anticipation, and fear—expressed in posts discussing brain-computer interface on X from 2010 to 2021. It indicates fluctuations in the presence of each emotion over time. Anticipation (light blue line) shows varied peaks and troughs throughout the timeline, with prominent peaks in 2010, 2013, and 2017. Trust (dark blue line) displays a more consistent pattern with smaller fluctuations and an increase toward the end of the period. Fear (purple line) remains relatively stable over the years, with slight peaks in 2012, 2015, and 2016, but generally shows lower percentages compared to anticipation and trust.