Large Scale Linguistic Processing of Tweets to Understand Social Interactions among Speakers of Less Resourced Languages: The Basque Case

Abstract

Social networks like Twitter are increasingly important in the creation of new ways of communication. They have also become useful tools for social and linguistic research due to the massive amounts of public textual data available. This is particularly important for less resourced languages, as it allows to apply current natural language processing techniques to large amounts of unstructured data. In this work, we study the linguistic and social aspects of young and adult people’s behaviour based on their tweets’ contents and the social relations that arise from them. With this objective in mind, we have gathered over 10 million tweets from more than 8000 users. First, we classified each user in terms of its life stage (young/adult) according to the writing style of their tweets. Second, we applied topic modelling techniques to the personal tweets to find the most popular topics according to life stages. Third, we established the relations and communities that emerge based on the retweets. We conclude that using large amounts of unstructured data provided by Twitter facilitates social research using computational techniques such as natural language processing, giving the opportunity both to segment communities based on demographic characteristics and to discover how they interact or relate to them.

Social analysis of young Basque-speaking communities in twitter

“…Current work substantially improves and extends the preliminary experimental work presented in (Fernandez de Landa et al, 2019). These improvements have led to a number of contributions.…”

“…Fourth, we took the 500 users at the top of the ranking to be young users and the 500 at the bottom to be adult. As a result, following this new method we obtain a set of 1,000 users (out of the original 8K users) classified as adult/young based on the initial formal/informal manual categorization of 1,000 tweets provided by Fernandez de Landa et al (2019).…”

“…More details can be found in (Agerri and Rigau, 2016;Agerri and Rigau, 2019). For this particular work we train the IXA pipes document classifier using the same experimental setup used in (Fernandez de Landa et al, 2019).…”

“…These improvements have led to a number of contributions. First, and taking as a starting point the Heldugazte corpus containing 6M tweets in Basque language (Fernandez de Landa et al, 2019), we devise a whole new methodology to classify users by life-stage (young/adult). This new method generates a new dataset, Heldugazte-Age, containing 80K tweets semi-automatically annotated at young/adult level.…”

Editorial for the Special Issue on “Natural Language Processing and Text Mining”

“…In the article "Large Scale Linguistic Processing of Tweets to Understand Social Interactions among Speakers of Less Resourced Languages: The Basque Case" [5], the authors study the linguistic and social aspects of the behavior of young and adult people. This study is carried out by of means of the linguistic analysis of the content of their tweets and the social relations that arise from them.…”