Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: DiSanto, Nick, Corso, Anthony, Sanders, Benjamin, Harding, Gavin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929209472974848
author DiSanto, Nick
Corso, Anthony
Sanders, Benjamin
Harding, Gavin
author_facet DiSanto, Nick
Corso, Anthony
Sanders, Benjamin
Harding, Gavin
contents While transformers have pioneered attention-driven architectures as a cornerstone of language modeling, their dependence on explicitly contextual information underscores limitations in their abilities to tacitly learn overarching textual themes. This study challenges the heuristic paradigm of performance benchmarking by investigating social media data as a source of distributed patterns. In stark contrast to networks that rely on capturing complex long-term dependencies, models of online data inherently lack structure and are forced to detect latent structures in the aggregate. To properly represent these abstract relationships, this research dissects empirical social media corpora into their elemental components, analyzing over two billion tweets across population-dense locations. We create Bag-of-Word embedding specific to each city and compare their respective representations. This finds that even amidst noisy data, geographic location has a considerable influence on online communication, and that hidden insights can be uncovered without the crutch of advanced algorithms. This evidence presents valuable geospatial implications in social science and challenges the notion that intricate models are prerequisites for pattern recognition in natural language. This aligns with the evolving landscape that questions the embrace of absolute interpretability over abstract understanding and bridges the divide between sophisticated frameworks and intangible relationships.
format Preprint
id arxiv_https___arxiv_org_abs_2310_05378
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data
DiSanto, Nick
Corso, Anthony
Sanders, Benjamin
Harding, Gavin
Computation and Language
Social and Information Networks
While transformers have pioneered attention-driven architectures as a cornerstone of language modeling, their dependence on explicitly contextual information underscores limitations in their abilities to tacitly learn overarching textual themes. This study challenges the heuristic paradigm of performance benchmarking by investigating social media data as a source of distributed patterns. In stark contrast to networks that rely on capturing complex long-term dependencies, models of online data inherently lack structure and are forced to detect latent structures in the aggregate. To properly represent these abstract relationships, this research dissects empirical social media corpora into their elemental components, analyzing over two billion tweets across population-dense locations. We create Bag-of-Word embedding specific to each city and compare their respective representations. This finds that even amidst noisy data, geographic location has a considerable influence on online communication, and that hidden insights can be uncovered without the crutch of advanced algorithms. This evidence presents valuable geospatial implications in social science and challenges the notion that intricate models are prerequisites for pattern recognition in natural language. This aligns with the evolving landscape that questions the embrace of absolute interpretability over abstract understanding and bridges the divide between sophisticated frameworks and intangible relationships.
title Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data
topic Computation and Language
Social and Information Networks
url https://arxiv.org/abs/2310.05378