Abstract Purpose Intuitionistic fuzzy set (IFS) has been found promising for handling ambiguity forms of uncertainty in social data. This paper undertakes an application of an intuitionistic fuzzy set in the social life cycle impact assessment (S-LCIA) of a public building project. This work proposes to combine an intuitionistic fuzzy set (IFS) with multi-attribute decision-making in converting qualitative data into quantitative social impacts of the building project. This research utilises IFS to accommodate and handle experts’ imprecise cognitions in S-LCIA to facilitate the identification and prioritisation of the most pressing indicators accompanying social impacts in a project. Methods Data were collected using questionnaire(s), structured interviews, and through targeted focus group sessions. Intuitionistic fuzzy set (IFS) approach was used to model the obtained data from structured interviews. Using IFS, this research also accounts for missing or ambiguous data that emerged during the data elicitation process. In combining IFS with multi-attribute decision-making techniques, the social impacts of selected stakeholders were evaluated using fuzzy set and IFS approaches. Sensitivity analysis was then used to test the robustness of the results and ranking was conducted based on each social stakeholder subcategory. Results and discussion Results revealed that approximately 23% of missing datapoints in the public case study building were incorporated in the S-LCIA using IFS. The issues of highest priority in each of the considered subcategory in the public case study building project according to IFS are (i) consumer privacy by adopting more functional planning (0.27), (ii) public commitment to sustainability (0.33), and (iii) education provided in the local community by having an indigenous botanical element for children (0.39), respectively. Conversely, the FS technique inferred that the issue of highest priority in the consumer stakeholder is the feedback mechanism (0.26). The overall degree of correlation between the IFS and FS is only 0.234, revealing that IFS provides a different perspective from conventional FS when used in modelling social data. Conclusion The IFS method provides an objective and systematic approach for dealing with a heterogeneous scope of imprecise and inexact social data in achieving holistic social life cycle assessment results. Furthermore, expansive stakeholder involvement would rely on a robust approach for improving social well-being in public buildings, thereby leaving no one behind in accomplishing a sustainable world.