When an expectation does not meet reality in a real-world situation, the difference is usually expressed and communicated via an act which is complaint. Customers often post reviews on the products or services they purchase on the retailer websites and different social media platforms, and the reviews may reflect complaints about the products or services. Automatic recognition of customers’ complaints on products or services that they purchase can be crucial for the organizations, multinationals and online retailers since they can exploit this information to fulfil the customers’ expectations including managing and resolving the complaints. In this work, we present the supervised and semi-supervised learning strategies to identify users’ complaints from the language they use to post their reviews. In other words, we automatically identify complaints from the opinionated texts (reviews) about products posted in Hindi. For this, first we automatically crawled the Hindi reviews on different products from the the websites of the retail giant Amazon and the popular social media platform YouTube, and prepared a gold-standard data set via a systematic manual annotation process. We use state-of-the-art classification algorithms for the complaints identification task and our classification models achieve reasonable classification accuracy (F1 = 68.38%) on a gold-standard evaluation test set.