Predicting User Demography and Device from News Comments

Rozen, Ohad; Oren, Joel; Raviv, Ariel

doi:10.1145/3404835.3463024

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This user interaction may be direct where gender identity is selfdeclared (user study or survey), or it may be indirect where gender identity is annotated or inferred (annotation of user-generated profile, facial inference). For example, Rozen et al [59] used userstated gender information to evaluate their proposed system in predicting user demographic attributes, namely gender, from user browsing data and generated comments on news articles.…”

Section: Overview Of Data and Univariate Findingsmentioning

confidence: 99%

“…Lastly, following critical work on automated gender recognition [35,65], we also advise against gender prediction in information access systems (the goal of 7 papers). Many of the papers we find in our data focused on gender prediction aim to make that determination from user behavior, such as written internet text [59] or more esoteric data such as spatial trajectories [69]. However, similar to our warning against gender personalization above, these predictions may perpetuate gender stereotypes and re-entrench them by making those determinations based on data instances which bear no relationship to gender, and will most likely misrepresent individuals who are transgender or gender non-conforming.…”

Section: When To Use Gender?mentioning

confidence: 99%

See 1 more Smart Citation

Much Ado About Gender: Current Practices and Future Recommendations for Appropriate Gender-Aware Information Access

Pinney,

Raj,

Hanna

et al. 2023

Preprint

View full text Add to dashboard Cite

Information access research (and development) sometimes makes use of gender, whether to report on the demographics of participants in a user study, as inputs to personalized results or recommendations, or to make systems gender-fair, amongst other purposes. This work makes a variety of assumptions about gender, however, that are not necessarily aligned with current understandings of what gender is, how it should be encoded, and how a gender variable should be ethically used. In this work, we present a systematic review of papers on information retrieval and recommender systems that mention gender in order to document how gender is currently being used in this field. We find that most papers mentioning gender do not use an explicit gender variable, but most of those that do either focus on contextualizing results of model performance, personalizing a system based on assumptions of user gender, or auditing a model's behavior for fairness or other privacyrelated issues. Moreover, most of the papers we review rely on a binary notion of gender, even if they acknowledge that gender cannot be split into two categories. We connect these findings with scholarship on gender theory and recent work on gender in humancomputer interaction and natural language processing. We conclude by making recommendations for ethical and well-grounded use of gender in building and researching information access systems. CCS CONCEPTS• Social and professional topics → Gender; • Information systems → Information retrieval.

show abstract

Section: Overview Of Data and Univariate Findingsmentioning

confidence: 99%

Section: When To Use Gender?mentioning

confidence: 99%