Online searches have been used to study different health-related behaviours, including monitoring disease outbreaks. An obvious caveat is that several reasons can motivate individuals to seek online information and models that are blind to people's motivations are of limited use and can even mislead. This is particularly true during extraordinary public health crisis, such as the ongoing pandemic, when fear, curiosity and many other reasons can lead individuals to search for healthrelated information, masking the disease-driven searches. However, health crisis can also offer an opportunity to disentangle between different drivers and learn about human behavior. Here, we focus on the two pandemics of the 21st century (2009-H1N1 flu and Covid-19) and propose a methodology to discriminate between search patterns linked to general information seeking (media driven) and search patterns possibly more associated with actual infection (disease driven). We show that by learning from such pandemic periods, with high anxiety and media hype, it is possible to select online searches and improve model performance both in pandemic and seasonal settings. Moreover, and despite the common claim that more data is always better, our results indicate that lower volume of the right data can be better than including large volumes of apparently similar data, especially in the long run. Our work provides a general framework that can be applied beyond specific events and diseases, and argues that algorithms can be improved simply by using less (better) data. This has important consequences, for example, to solve the accuracy-explainability trade-off in machine-learning.However, if we could decouple searches mostly driven by media, anxiety, or curiosity, from the ones related with actual disease, we could not only improve disease monitoring, we could also deepen our understanding of online human behavior. In the case of Google search trends, identifying what terms are more correlated with media exposure and reducing their influence in the model is crucial to correct past errors.In this paper, we propose that the characteristics that make pandemics unique and hard to now-cast, such as media hype, can also be used as opportunities for two main reasons: 1) as pandemics tend to exacerbate behaviors, the noise (media) is of the same order of magnitude as the signal (cases), making it more visible, allowing us to discriminate between the two; and 2) because information seeking becomes less common as the pandemic progresses 18, 28 and these different dynamics can be used when selecting the search terms. In fact, instead of ignoring pandemic periods, studying what happens during the worst possible moment can help us understand which are the search-terms more associated with the disease and the ones that were prompted by media exposure. This solution might avoid over-fitting and enable the predictive model to be more robust over time, especially during seasonal events. Therefore, we focus on the only two XXI century WHO declared pandemics and aim ...