Titulo Estágio
Event Audience Profiling
Área Tecnológica
Inteligência Artificial
Local do Estágio
DEI - AmILab
Enquadramento
Nowadays, the most relevant events in the city are advertised online, however this information is usually in the form of unstructured text (natural language), which hinders the exploitation of the full potential of such wealthy information for example in modeling urban mobility.
In the AmILab/CMS, we have been working with the Natural Language Processing (NLP) techniques in order to transform this unstructured information in structured knowledge that can be used, for example, to estimate the impact that events have on transportations systems.
One of the key aspects in understanding the impact of events on the city dynamics is related with their target audience profiles. It is well known that events with different audiences cause different impact patterns in the city (e.g. events with a more foreigner public may originate more taxi trips, while events for a younger audience are more likely to translate in more public transport trips).
In our project InfoCrowds (funded by FCT), one of the main tasks is to correlate mobility with event semantics. With rich information on events, we should be able to understand its mobility implications. The role of the student in this project is to work on the event analysis side, particularly on building target audience profiles for events.
Objetivo
In line with the work currently under development in our lab, the goal is to build target audience profiles of special events (e.g. music concerts, art exhibits, comedy shows, artistic performances, sales, etc.) by analysing their textual description along with other characteristics. Note that this information might deem insufficient, hence the use of semantic enrichment tools, external resources (e.g. Wikipedia) and social networks (Facebook and Twitter) might be necessary to accurately predict a target audience of an event.
Plano de Trabalhos - Semestre 1
The tentative plan for this project (semester 1) is the following:
- October 15th - State of the art. (1.5 months)
- October 31st - Understanding previous work in the lab. (2 months)
- November 30th - Event Audience Profiler, Part I. (1 month)
- December 31th - Experimentation. (1 month)
- January 31th - Intermediate report. Plan for new developments on the system of the following semester. Possible topics include the use of semantic enrichment tools, external resources (e.g. Wikipedia) and social networks (Facebook and Twitter). (1 month)
Plano de Trabalhos - Semestre 2
The tentative plan for this project (semester 2) is the following:
- April 30th - Event Audience Profiler, Part II: Implementation of new developments (3 months)
- May 31th - Experiments report. Paper submission. (1 month)
- June 30th - MSc thesis delivery. (1 month)
Condições
Strong skills in programming (Java, Python).
Other interesting (optional) skills/interests include Machine Learning and Natural Language Processing techniques.
Will to communicate in English with other researchers is also important.
Observações
The candidate curriculum is required. There is also a possibility of funding for this work in the second semester.
Orientador
Ana Cristina Alves e Carlos Lisboa Bento
bento@dei.uc.pt 📩