In the big data context, the growing volume of textual data presents challenges for traditional structured data-based decision support systems (DSS). DSS based on structured data is difficult to process the semantic information of text data. To meet the challenge, this thesis proposes a solution for the Decision Support System (DSS) based on machine Learning and qualitative analysis, namely TLE-DSS. TLE-DSS refers to three critical analytical modules: Thematic Analysis (TA), Latent Dirichlet Allocation (LDA)and Evolutionary Grounded Theory (EGT). To better understand the operation mechanism of TLE-DSS, this thesis used an experimental case to explain how to make decisions through TLE-DSS. Additionally, during the data analysis of the experimental case, by calculating the difference of perplexity of different models to compare similarities, this thesis proposed a solution to determine the optimal number of topics in LDA. Meanwhile, by using LDAvis, a model with the optimal number of topics was visualized. Moreover, the thesis also expounded the principle and application value of EGT. In the last part, this thesis discussed the challenges and potential ethical issues that TLE-DSS still faces.