Mrini, KhalilSharma, KshitijDillenbourg, Pierre2018-08-132018-08-132018-08-132017https://infoscience.epfl.ch/handle/20.500.14299/147744We present an automatic method for trend detection in job ads. From a job-posting website, we collect job ads from 16 countries and in 8 languages and 6 job domains. We pre-process them by removing stop words, lemmatising and performing cross-domain filtering. Then, we improve the vocabulary by forming n-grams and restrict it by filtering based on named-entity and part-of-speech tags. We split the job ads to compare two time periods: the first halves of 2016 and 2017. A trending word is defined as a word with a higher TF-IDF weight in 2017 than in 2016. The results obtained show a close correlation between the position of a word in its text and its trendiness regardless of country, language or job domain.Natural Language ProcessingTrend DetectionKeyword ExtractionCross-Domain FilteringTraining NeedsText Miningtext::report::research report