JobTrends

Given the growing reliance on informal platforms, such as Tele-gram for job vacancy announcements, traditional approaches to jobtitle classification face challenges including noisy text, overlappingsemantics between roles, and severe class imbalance. To enable ro-bust and generalizable modeling across heterogeneous recruitmentsources, we present JobTrends, a large-scale, multi-source datasetof job postings collected from LinkedIn, Hahu Jobs, and Telegram.The dataset is released in four complementary versions: (1) a rawcorpus of 381 088 job postings, (2) a cleaned and standardized ver-sion containing 353 899 entries, (3) a computer science–specificsubset with 55 686 postings, and (4) its manually annotated andcleaned counterpart. The computer science subset spans 10 occupa-tional categoriesBy combining data from formal (LinkedIn, Hahu)and informal (Telegram) sources, JobTrends represents the broadvariability and stylistic range of real-world recruitment language.To showcase its utility, we describe the collection and organizationprocess of JobTrends and report baseline results using machinelearning and transformer-based models. While models show vary-ing strengths across dominant and minority classes, the bench-marks establish reference points for future work and highlight thedataset’s potential for advancing research in automated recruitmentanalytics.