Quantification of Gender Bias and Sentiment Toward Political Leaders Over 20 Years of Kenyan News Using Natural Language Processing

Abstract

Background: Despite a 2010 Kenyan constitutional amendment limiting members of elected public bodies to < two-thirds of the same gender, only 22 percent of the 12th Parliament members inaugurated in 2017 were women. Investigating gender bias in the media is a useful tool for understanding socio-cultural barriers to implementing legislation for gender equality. Natural language processing (NLP) methods, such as word embedding and sentiment analysis, can efficiently quantify media biases at a scope previously unavailable in the social sciences.Methods: We trained GloVe and word2vec word embeddings on text from 1998 to 2019 from Kenya’s Daily Nation newspaper. We measured gender bias in these embeddings and used sentiment analysis to predict quantitative sentiment scores for sentences surrounding female leader names compared to male leader names.Results: Bias in leadership words for men and women measured from Daily Nation word embeddings corresponded to temporal trends in men and women’s participation in political leadership (i.e., parliamentary seats) using GloVe (correlation 0.8936, p = 0.0067, r2 = 0.799) and word2vec (correlation 0.844, p = 0.0169, r2 = 0.712) algorithms. Women continue to be associated with domestic terms while men continue to be associated with influence terms, for both regular gender words and female and male political leaders’ names. Male words (e.g., he, him, man) were mentioned 1.84 million more times than female words from 1998 to 2019. Sentiment analysis showed an increase in relative negative sentiment associated with female leaders (p = 0.0152) and an increase in positive sentiment associated with male leaders over time (p = 0.0216).Conclusion: Natural language processing is a powerful method for gaining insights into and quantifying trends in gender biases and sentiment in news media. We found evidence of improvement in gender equality but also a backlash from increased female representation in high-level governmental leadership.

Intricacies for Gender Equality in Formal and Informal Structures through Governance Enhancement; a Kenyan Perspective

“…Additionally, we had only 18 nominated women senators not elected and 76 out of 1050 women elected to county assembly as illustrated in figure 3 which paints a clear picture of gender inequalities (Hewitt, 2018;Opoku et al, 2018). In 2017, there was a positive gain with more women elected in governor and senator positions and that 25% of the government comprises of female politicians (Kantar, 2021;Pair et al, 2021).…”

“…Intergenerational effects and witnessing or experiencing Gender Based Violence (GBV) by a child in the home have future consequences on the outlook of gender-based violence by girls and violence socialization by boys (Pair et al, 2021). The essence of governance enhancement in formal structures provides a ray of hope for victims of gender violations through transparency and accountability in handling the perpetrators of these gender biases and harmful practices (Doumbia, 2019;Schwab et al, 2019).…”

“…This positive strides can be reinforced further through governance where the pillars of inclusivity, equity, and responsiveness safeguard that a balanced gender representation in learning institutions create synergy and efficacy required (Karar & Jacobs-Mata, 2016;Rutherford & Buss, 2019). Subsequently in the informal structures, governance pillars of the rule of law, inclusivity and consensus orientation would strengthen gender equality policies that seek to curtail biased patriarchal persuasions against women and education (International Labour Office, 2008;Milazzo & Goldstein, 2019;Pair et al, 2021). Governance effectiveness -0.63 -0.56 -0.57 -0.52 -0.46 -0.33 -0.30 -0.32 -0.32 -0.41 Rule of law -1.01 -0.94 -0.90 -0.82 -0.71 -0.42 -0.49 -0.44 -0.41 -0.41 Control of corruption -1.06 -0.91 -0.95 -1.09 -1.03 -0.93 -1.01 -0.89 -0.95 -0.85 Regulatory control -.15 -0.08 -0.21 -0.30 -0.30 -0.32 -0.31 -0.30 -0.23 -0.23 Source: (World Bank, 2020) The relationship between governance and good development is clearly illustrated in Table 1 indicating a positive correlation between governance and per capita income (Doumbia, 2019;World Bank, 2020).…”

Gender bias in consumer perceptions: The case of agro-input dealers in Uganda

“…Gender equity bias is also pervasive in politics. Pair et al (2021) use natural language processing (NLP) to search for gender bias in Kenya's leading newspaper and sentiment analysis to predict quantitative sentiment scores for sentences surrounding female leader names compared to male leader names. They nd evidence of improvement in gender equality but also a backlash from increased female representation in high-level governmental leadership.…”

“…The prevalence of gender equity bias in the context of agro-input dealers again underscores the importance of customs and norms in rural societies. Interventions and initiatives that focus solely on increasing women's empowerment are unlikely to be sucient, and may in some cases even backre (Pair et al, 2021). It will be important to challenge gender stereotypes and role congruence and such interventions should not focus on only one gender.…”