@inproceedings{kumar-etal-2026-human,
    title = "Human-Centered Supervision for Sentiment Analysis in {T}elugu: A Systematic Inquiry Beyond Accuracy",
    author = "Kumar, Vallabhaneni Raj  and
      S, Ashwin  and
      Manna, Supriya  and
      Sett, Niladri  and
      Harshitha, Cheedella V S N M S Hema  and
      Harshitha, Kurakula  and
      Deepakraj, Basina  and
      Sharma, Anand Kumar  and
      Sarkar, Tanuj  and
      Shakeer, Samanthapudi  and
      Krishna, Bondada Navaneeth",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1476/",
    pages = "29519--29537",
    ISBN = "979-8-89176-395-1",
    abstract = "Sentiment analysis for low-resource languages remains challenging in an era where interpretability, human alignment, and fairness are increasingly non-negotiable aspects of modern machine learning systems. These challenges stem both from the scarcity of annotated data and from the resulting difficulty of conducting reliable, human-interpretable analyses that go beyond predictive accuracy. Telugu, one of the primary Dravidian languages with over 96 million speakers, is not an exception. In this work, we first introduce TeSent, a large-scale Telugu sentiment classification dataset annotated with sentiment labels and human-selected rationales from multiple native speakers. This resource enables the study of rationale-based supervision for aligning models with human reasoning in this low-resource setting. We fine-tune five transformer-based models with and without rationale supervision and evaluate them on classification performance, explanation quality, and social bias. To facilitate controlled fairness evaluation, we additionally construct TeEEC, an evaluation corpus for Telugu sentiment analysis. Our results show that incorporating human rationales consistently improves alignment and often leads to holistic gains in predictive performance. We further provide extensive analysis of multi-facade explanation quality and fairness, offering insights into the broader effects of alignment-oriented supervision in resource-scarce language contexts."
}