A novel ensemble approach based on MCC and MCDM methods for prioritizing tweets mentioning urban issues in smart city

Abstract

Purpose

Social media platform, like Twitter, has increasingly become the mode of reporting civic issues owing to their vast and fast reachability. A tremendous amount of information on urban issues is shared every moment out of which some tweets may need immediate attention to save lives or avoid future disasters. Existing approaches are only limited to the identification of complaint tweets; however, its prioritization based on urgency is still unexplored. This study aims to decide the ranking of complaints based on its criticality derived using multiple parameters, like type of complaint, season, day or night, gender, holiday or working day, etc.

Design/methodology/approach

The approach proposes an ensemble of multi-class classification (MCC) and “two-level” multi-criteria decision-making (MCDM) algorithms, like AHP and TOPSIS, to evaluate the accurate ranking score of the tweet based on the severity of the issue. Initially, the MCC is applied to tweets to categorize the tweets into three categories, i.e. moderate, urgent and immediate. Further, the first level of MCDM algorithm decides the ranking within each complaint type, and the second level evaluates the ranking across all types. Integration of MCC and MCDM methods further helps to increase the accuracy of the result.

Findings

The paper discusses various parameters and investigates how their combination plays a significant role in deciding the priority of complaints. It successfully demonstrates that MCDM techniques are helpful in generating the ranking score of tweets based on various criteria.

Originality/value

This paper fulfills an identified need to prioritize the complaint tweet which helps the local government to take time-bound actions and save a life.

Citation

Yenkar, P.P. and Sawarkar, S.D. (2023), "A novel ensemble approach based on MCC and MCDM methods for prioritizing tweets mentioning urban issues in smart city", Kybernetes, Vol. 52 No. 9, pp. 3613-3646. https://doi.org/10.1108/K-08-2021-0785