UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis

Abstract

Global models are typically trained to be as generalizable as possible. Invariance to the specific user is considered desirable since models are shared across multitudes of users. However, these models are often unable to produce personalized responses for individual users, based on their data. Contrary to widely-used personalization techniques based on few-shot and meta-learning, we propose UserIdentifier, a novel scheme for training a single shared model for all users. Our approach produces personalized responses by prepending a fixed, user-specific non-trainable string (called "user identifier") to each user's input text. Unlike prior work, this method doesn't need any additional model parameters, any extra rounds of personal few-shot learning, or any change made to the vocabulary. We empirically study different types of user identifiers (numeric, alphanumeric, and also randomly generated) and demonstrate that, surprisingly, randomly generated user identifiers outperform the prefixtuning based state-of-the-art approach by up to 13%, on a suite of sentiment analysis datasets.

Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback

“…4 For example, a title keyword search for 'personali' or 'personaliz' returns 124 articles from the ACL Anthology and a further 10 from the arXiv Computation and Language (cs.CL) subclass. These systems cover a wide range of tasks including dialogue [127,157,36,39,41,109,133,146,149,206,238,244], recipe or diet generation [147,87,159], summarisation [215,240], machine translation [156,153,194,237], QA [137,193], search and information retrieval [4,40,59,70,245], sentiment analysis [80,155,226], domain classification [129,114,113], entity resolution [132], and aggression or abuse detection [107,108]; and are applied to a number of societal domains such as education [118,163,241], medicine [3,15,225,235] and news consumption…”

Unifying Data Perspectivism and Personalization: An Application to Social Norms

“…A similarity between personalization and annotator modeling is that the most common approach appears to be using author IDs. These have been used, for instance, in sentiment analysis (Mireshghallah et al, 2021), sarcasm detection (Kolchinski and Potts, 2018), and query autocompletion (Jaech and Ostendorf, 2018). King and Cook (2020) evaluated methods of personalized language modeling, including priming, interpolation, and fine-tuning of n-gram and neural language models.…”