Co-occurrence networks of Twitter content after manual or automatic processing. A case-study on “gluten-free”

Abstract

Gathering information from social networks such as Twitter has emerged to obtain spontaneous and direct opinions of users about a topic. This study focuses on using co-occurrence networks to analyse Twitter information. The objectives were to study the impact of text pre-treatment (codification based in qualitative analysis or just pre-cleaning) and to apply co-occurrence networks for analysing what is said on Twitter about specific topics like "gluten-free". As such, 16,386 tweets in Spanish containing terms "sin-gluten" and "gluten-free" were collected. A subset of 3,000 tweets was used to make co-occurrence networks two ways: i) from the manually coded text and ii) from pre-cleaned text. Results indicate that the co-occurrence network from pre-cleaned text provides meaningful information showing structure and relevance for terms like the network from coded text. The whole set of tweets was used to explore Twitter information about gluten-free, showing users share information about products, occasions, social situations, and places but also to product characteristics, sensations, and diet or health issues related to the products. Five product categories, critical for the lack of gluten (bread, cake, cookie, beer, and pizza) occupied most tweets, and according to the related terms were intended to recommend how to get (buying or cooking) these gluten-free products and to exhibit what (how, when, and where) they prepare and eat. These aspects were different among products and separated co-occurrence networks allowed better identification.

Cross-Societal Analysis of Climate Change Awareness and Its Relation to SDG 13: A Knowledge Synthesis from Text Mining

“…Nevertheless, there are many advantages, such as collecting information suitable for the purpose from welldesigned questionnaires as well as abundant individual-level background information of respondent groups [55,59,60]. The text analytic method based on computer-assisted learning has recently emerged to complement these limitations of empirical surveys [38,61]. Text mining techniques have also been utilized to elicit valuable insights from the data surveyed by empirical methods [30].…”

Making Full Use of Qualitative Data to Generate New Fish Product Ideas through Co-Creation with Consumers: A Methodological Approach

“…The manual merging through the first pseudo-triangulation process allowed us to perform a more thorough and goal-oriented reduction in the content. Therefore, the manual merging into high-order codes allowed for the maintenance of the information contained in the less frequently mentioned words, although this can possibly lead to a loss of information nuance [ 26 ]. Nevertheless, a loss of information and word misinterpretation are two major errors that can be mitigated during manual merging if the context of some words is considered during the pseudo-triangulation process.…”

“…In contrast, word frequency counting is probably the most widespread software-assisted method, as it is a simple and rapid way to summarise the results in terms of the most frequently mentioned words [ 26 ]. Hence, word frequency counting is commonly used in qualitative research as, for example, an indicator of the importance of certain words for participants [ 27 , 28 , 29 , 30 ].…”

Building a data‐driven circular supply chain hierarchical structure: Resource recovery implementation drives circular business strategy

“…In particular, the inductive type of content analysis is used to identify the occurrence of keywords in a social media source. Among social media platforms, Twitter is one of the most prominent and rapidly increasing microblogging services including a high volume of text‐based messages and named tweets created by active users daily (Puerta et al, 2020). Twitter information appears to be one of the most extensively employed data sources for academic research and practical applications.…”