Predicting user behavior using data profiling and hidden Markov model

<span lang="EN-US">Mental health disorders affect many aspects of patient’s lives, including emotions, cognition, and especially behaviors. E-health technology helps to collect information wealth in a non-invasive manner, which represents promising opportunity construct behavior markers. Combining such user data can provide more comprehensive contextual view than questionnaire data. Due behavioral data, we train machine learning models understand the pattern also use prediction algorithms know next state person’s behavior. The remaining challenges for this issue are how apply mathematical formulations textual datasets find metadata that aids identify life <span>predict his comportment. main idea work is hidden Markov model (HMM) predict from social media applications by analyzing detecting states symbols user</span> dataset. To achieve goal, need analyze detect dataset, then convert numerical matrices. Finally, HMM states. We tested our program identified log-likelihood was higher better when fits In any case, results study indicated suitable purpose yielded valuable data.</span>