Colour Coded Emotion Classification in Mental Health Social Media

Neil Vaughan, Maurice Mulvenna, RR Bond

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

146 Downloads (Pure)


This research applies emotion detection to messages from online mental health social media. In particular, this focusses on specialised social media for users to report health or mental health problems. Automatically detecting the emotion in social media can help to rapidly identify any concerning problems which could benefit from intervention aiming to prevent self-harming or suicide. Detecting emotions enables messages to be colour coordinated according to the emotion to enhance the human-computer interaction. A supervised classification method is applied to a labelled dataset and results presented. A prototype user interface system is developed based on detecting emotion, colour coding the message to display detected emotions to users in real-time.
Original languageEnglish
Title of host publication Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018)
EditorsRaymond Bond, Maurice Mulvenna, Jonathan Wallace, Michaela Black
Place of PublicationSwindon, UK
PublisherBCS Learning & Development Ltd
Number of pages5
Publication statusPublished (in print/issue) - 10 May 2018
EventBritish HCI Conference 2018 - Belfast, Belfast, Northern Ireland
Duration: 2 Jul 20186 Jul 2018


ConferenceBritish HCI Conference 2018
Abbreviated titleBHCI2018
Country/TerritoryNorthern Ireland


  • Affective computing
  • emotion
  • mental health
  • social media


Dive into the research topics of 'Colour Coded Emotion Classification in Mental Health Social Media'. Together they form a unique fingerprint.

Cite this