Social Media Analysis: Twitter Vigilance

Due to their popularity and rapid propagation capability, social media have become important communication channels on public opinions on real world events. Multiple organizations and governments recognize the importance of social media as public opinion sensing tools that can be used to monitor special events like natural hazards such as earthquakes, landslides, floods, storms to develop early warning systems, but also via monitoring the total volume of tweets on particular events could be used to predict presences at for example special cultural events.

The Twitter Vigilance tool is used also in international projects and challenges to monitor and assess social media impact, reputation in real time. In such cases, the tool is used for monitoring, evaluating and detecting and assessing:

  • critical events and conditions, user opinions of the city's response to events, appreciation of actors and stories;
  • reputation of services, proneness of social impact, political assessments;
  • Impact of marketing campaigns, advertising impact;
  • prediction of number of people, attendees at events, TV shown.

Twitter Vigilance is a multi-user tool for Twitter analysis on which it is possible to monitor simple and complex information channels by combining multiple research keywords. In detail the solution:

  • is based on the definition of Twitter Channel which consists of a set of simple and complex queries performed on Twitter platform;
  • the simplest Twitter Channel monitored can control tweets referred to a single hashtag, or to a single keyword. Complex Channels consist of tens of complex queries according to Twitter syntax combined with keywords, hashtags, etc.;
  • ensures the anlaysis of 98% of tweets/retweets referred to events by providing the yield and precision evidence;
  • is capable to monitor and analyse slow and explosive events on Twitter with the same efficiency and precision;
  • provides adaptive algorithms to allow effectively cope with slow events that become explosive without losses;
  • provides in addition to the Tweets Flow Analysis (volume of tweets/retweets) also Advanced Artificial Intelligence Natural Language Processing Analysis providing also the Sentiment Analysis on multiple languages (English, Spanish, French, Italian).

The Twitter Vigilance tool is active since April 2015. Active Channels on Twitter vigilance as hundreds of different scenarios and goals: EXPO, Florence Tourism, pharmacovigilance, Tuscany weather alert, civil protection, and many more.

The Twitter Vigilance tool can be used to perform analysis for marketing and communication purposes, participatory assessment of citizens, etc., and in particular to:

  • discover and evaluate trends;
  • perform predictive assessments, attendance, audience acceptance levels;
  • perform competitor analysis and carry out evaluations of appreciation or not of people, products and advertisements;
  • detecting emerging trends.

The Twitter Vigilance tool performs automated analysis and early warning taking into account, multiple channels, tags, hashtags, and:

  • tweets and retweets;
  • keywords, verbs, and adjectives;
  • positive/negative impact, known as sentiment analysis.

The solutions adopted are based on the ultimate technologies for natural language  processing, and artificial intelligence as BERT in multilingual: Italia, English, France, Spain, and Greece.

Several papers have been published by DISIT lab about the usage of the tool in several projects such as: REPLICATE, RESOLUTE, Snap4City,  Herit-Data, etc.

Read more on:


  • V. Grasso, A. Crisci, M. Morabito, P. Nesi, G. Pantaleo, I. Zaza, B. Gozzini, "Italian codified hashtags for weather warning on Twitter–who is really using them?." Advances in Science and Research 14 (2017): 63-69. , 16th EMS Annual Meeting & 11th European Conference on Applied Climatology (ECAC), 12–16 September 2016 | Trieste, Italy, CE2/AM3, Delivery and communication of impact based forecasts and risk based warnings. ; Grasso, V., Crisci, A., Morabito, M., Nesi, P., Pantaleo, G., Zaza, I., and Gozzini, B.: Italian codified hashtags for weather warning on Twitter – who is really using them?, Adv. Sci. Res., 14, 63-69, doi:10.5194/asr-14-63-2017, 2017. doi:10.5194/asr-14-63-2017
  • D. Cenni, P. Nesi, G. Pantaleo, I. Zaza, "Twitter Vigilance: a Multi-User platform for Cross-Domain Twitter Data Analytics, NLP and Sentiment Analysis", IEEE international Conference on Smart City and Innovation, 2017, San Francisco.