Credibility reasoning has attracted a lot of attention due to its distinguished power and efficiency in representing uncertainty and vagueness within the process of reasoning and decision making. Aiming at the problem of inaccurate credibility estimation in uncertainty reasoning and making experts to express hesitant preferences better in evaluation reasoning process, this paper introduces hesitant fuzzy linguistic term set into credibility uncertainty reasoning. First, we propose hesitant fuzzy linguistic-valued credibility (HLCF), and establish the knowledge representation model of the hesitant fuzzy linguistic-valued credibility. Then, in order to solve the problem of incomplete information in the evaluation reasoning process, an information complement algorithm based on maximum similarity is constructed. After that, the algorithms of single rule and multiple rules of parallel relationship of hesitant fuzzy linguistic-valued credibility are proposed to enrich the reasoning rule base and get more accurate reasoning results. The closeness degrees between the conclusions of each alternative after reasoning and the expected value are calculated, so as to select the most suitable alternative. Finally, a practical example which concerned the social risk analysis is given to illustrate the applicability and effectiveness of the proposed approach.