Analyzing fair skin preference in Indian society: A case study on matrimonial advertisements using web mining and text analytics

Marriage remains a critical as well as sacred institution in India, with arranged marriages continuing as a dominant practice. Newspapers, with a readership exceeding 425 million, serve as a primary medium for matrimonial advertisements and thus provide an effective data source for analyzing social preferences. One recurring attribute in these advertisements is the emphasis on fair skin, historically associated with caste, class, and socio-economic advantage. Despite globalization and technological change, this preference persists, often reinforced by media and market dynamics. This paper presents a computational analysis of matrimonial advertisements collected from 30 newspapers in multiple Indian languages over the period 2010–2024. A web-scraper was designed to construct a structured database of advertisements, followed by query-based text analytics for extracting and categorizing skin-colour references. A pseudo-code description of the framework is provided to detail the methodological workflow. Temporal frequency distributions and keyword analyses were generated to examine longitudinal trends in the expression of skin-color preference. The results indicate a consistent and significant bias toward fair skin descriptors throughout the study period, with limited evidence of decline despite broader sociocultural shifts. The findings highlight how entrenched cultural norms, amplified by market influences, continue to govern partner selection criteria in India. This study demonstrates the value of applying large-scale text analytics to traditional print media for uncovering persistent socio-cultural patterns. • Marriage is considered a sacred ceremony in Indian society. • Darker skin is considered inferior to fairer skin. • After independence, India has achieved many milestones towards equality. • Indian matrimonial advertisements present a different view of societal progress. • Research highlights that whiter skin is still considered superior when finalising matrimonial relationships.