Efficient Use of Large Language Models for Analysis of Text Corpora

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F24%3AA2502N5Z" target="_blank" >RIV/61988987:17610/24:A2502N5Z - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/24:00381571

Výsledek na webu

<a href="https://www.scitepress.org/Papers/2024/123498/123498.pdf" target="_blank" >https://www.scitepress.org/Papers/2024/123498/123498.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0012349800003654" target="_blank" >10.5220/0012349800003654</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Use of Large Language Models for Analysis of Text Corpora

Popis výsledku v původním jazyce

In this paper, we propose an efficient approach for tracking a given phenomenon in a corpus using natural language processing (NLP) methods. The topic of tracking phenomena in a corpus is important, especially in the fields of sociology, psychology, and economics, which study human behavior in society. Unlike existing approaches that rely on universal large language models (LLMs), which are computationally expensive, we focus on using computationally less expensive methods. These methods allow for high data processing speed while maintaining high accuracy. Our approach is inspired by the cascade approach to optimization, where we first roughly filter out unwanted information and then gradually use more accurate models, which are computationally more expensive. In this way, we are able to process large amounts of data with high accuracy using different models, while also reducing the overall cost of computations. To demonstrate the proposed method, we chose a task that consists of finding the frequency of occurrence of a certain phenomenon in a large text corpus, which is divided into individual months of the year. In practice, this means that we can, for example, use Internet discussions to find out how much people are discussing a particular topic. The entire solution is presented as a pipeline, which consists of individual phases that successively process text data using methods selected to minimize the overall cost of processing all data.

Název v anglickém jazyce

Efficient Use of Large Language Models for Analysis of Text Corpora

Popis výsledku anglicky

In this paper, we propose an efficient approach for tracking a given phenomenon in a corpus using natural language processing (NLP) methods. The topic of tracking phenomena in a corpus is important, especially in the fields of sociology, psychology, and economics, which study human behavior in society. Unlike existing approaches that rely on universal large language models (LLMs), which are computationally expensive, we focus on using computationally less expensive methods. These methods allow for high data processing speed while maintaining high accuracy. Our approach is inspired by the cascade approach to optimization, where we first roughly filter out unwanted information and then gradually use more accurate models, which are computationally more expensive. In this way, we are able to process large amounts of data with high accuracy using different models, while also reducing the overall cost of computations. To demonstrate the proposed method, we chose a task that consists of finding the frequency of occurrence of a certain phenomenon in a large text corpus, which is divided into individual months of the year. In practice, this means that we can, for example, use Internet discussions to find out how much people are discussing a particular topic. The entire solution is presented as a pipeline, which consists of individual phases that successively process text data using methods selected to minimize the overall cost of processing all data.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICPRAM 2024

ISBN

978-989758684-2

ISSN

2184-4313

e-ISSN

—

Počet stran výsledku

11

Strana od-do

695-705

Název nakladatele

—

Místo vydání

Roma, Italy

Místo konání akce

Roma, Italy

Datum konání akce

28. 1. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—