Systematic Literature Review of Topic Labeling

The rapid growth of textual data on the web has led researchers to develop methods in Natural Language Processing (NLP) to process, understand, and identify topics. Among these methods, Topic Modeling helps extract relevant topics, represented as clusters of words. However, interpreting these clusters into meaningful topics remains a challenge. This limitation has led to further research into topic labeling, an approach for assigning comprehensive and semantically meaningful labels to topic modeling results, ensuring that they are interpretable and understandable from a human perspective. In this paper, we present a Systematic Literature Review (SLR) on topic labeling. This review explores its definition, geographical and time distribution, methodologies, datasets, evaluation methods, successes, and challenges. This paper presents an SLR on topic labeling, synthesizing insights from 41 high-quality studies. It serves as a rich source of information for researchers interested in investigating different approaches for discovering topics within textual data. It addresses the various aspects of topic labeling and includes discussions that highlight the challenges of this approach, encouraging further research in this field.