RESUMO
Searching social media to find relevant semantic domains often results in large text files, many of which are irrelevant due to cross-domain content resulting from word polysemy, abstractness, and degree centrality. Through an iterative pruning process, Cascaded Semantic Fractionation (CSF) systematically removes these cross-domain links. The social network procedure performs community detection in semantic networks, locates the semantic groups containing the terms of interest, excludes intergroup links, and repeats community detection on the pruned intragroup network until the domain of interest is clarified. To illustrate CSF, we analyzed public Facebook posts, using the CrowdTangle app for historical data search, from February 3, 2020, to March 13, 2021, about the possible Wuhan lab leak of COVID-19 over a daily interval. The initial search using keywords located six multi-day bursts of posts of more than 500 per day among 95 K posts. These posts were network analyzed to find the domain of interest using the iterative community detection and pruning process. CSF can be applied to capture the evolutions in semantic domains over time. At the outset, the lab leak theory was presented in conspiracy theory terms. Over time, the conspiratorial elements washed out in favor of an accidental release as the issue moved from social to mainstream media and official government views. CSF identified the relevant social media semantic domain and tracked its changes.
RESUMO
Sentiment research is dominated by studies that assign texts to positive and negative categories. This classification is often based on a bag-of-words approach that counts the frequencies of sentiment terms from a predefined vocabulary, ignoring the contexts for these words. We test an aspect-based network analysis model that computes sentiment about an entity from the shortest paths between the sentiment words and the target word across a corpus. Two ground-truth datasets in which human annotators judged whether tweets were positive or negative enabled testing the internal and external validity of the automated network-based method, evaluating the extent to which this approach's scoring corresponds to the annotations. We found that tweets annotated as negative had an automated negativity score that was nearly twice as strong than positivity, while positively annotated tweets were six times stronger in positivity than negativity. To assess the predictive validity of the approach, we analyzed sentiment associated with coronavirus coverage in television news from January 1 to March 25, 2020. Support was found for the four hypotheses tested, demonstrating the utility of the approach. H1: broadcast news expresses less sentiment about coronavirus, panic, and social distancing than non-broadcast news outlets. H2: there is a negative bias in the news across channels. H3: sentiment increases are associated with an increased volume of news stories. H4: sentiment is associated with uncertainty in news coverage of coronavirus over time. We also found that as the type of channel moved from broadcast network news to 24-h business, general, and foreign news sentiment increased for coronavirus, panic, and social distancing.
