# Sentiment and structure in word co-occurrence networks on Twitter

arXiv: https://arxiv.org/abs/2110.00587 · HTML: https://mlsanity.com/paper/2110.00587/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 76 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Stance and Sentiment in Tweets](https://mlsanity.com/paper/1605.01655/) (2016)
- [Sentiment Analysis of Twitter Data for Predicting Stock Market Movements](https://mlsanity.com/paper/1610.09225/) (2016)
- [Forecasting the onset and course of mental illness with Twitter data](https://mlsanity.com/paper/1608.07740/) (2016)
- [A network approach to topic models](https://mlsanity.com/paper/1708.01677/) (2017)
- [Human language reveals a universal positivity bias](https://mlsanity.com/paper/1406.3855/) (2014)
- [Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose](https://mlsanity.com/paper/1306.5204/) (2013)
- [Storywrangler: A massive exploratorium for sociolinguistic, cultural, socioeconomic, and political timelines using Twitter](https://mlsanity.com/paper/2007.12988/) (2020)
- [Zipf's law holds for phrases, not words](https://mlsanity.com/paper/1406.5181/) (2014)
- [Network Backboning with Noisy Data](https://mlsanity.com/paper/1701.07336/) (2017)
- [Text mixing shapes the anatomy of rank-frequency distributions: A modern Zipfian mechanics for natural language](https://mlsanity.com/paper/1409.3870/) (2014)
- [On Positivity Bias in Negative Reviews](https://mlsanity.com/paper/2106.12056/) (2021)
- [Public Opinion Polling with Twitter](https://mlsanity.com/paper/1608.02024/) (2016)
- [Fame and Ultrafame: Measuring and comparing daily levels of `being talked about' for United States' presidents, their rivals, God, countries, and K-pop](https://mlsanity.com/paper/1910.00149/) (2019)
- [Quantifying language changes surrounding mental health on Twitter](https://mlsanity.com/paper/2106.01481/) (2021)
- [Say Their Names: Resurgence in the collective attention toward Black victims of fatal police violence following the death of George Floyd](https://mlsanity.com/paper/2106.10281/) (2021)
- [Augmenting semantic lexicons using word embeddings and transfer learning](https://mlsanity.com/paper/2109.09010/) (2021)

## Built on by (most cited first, 2 of 2)

- [A decomposition of book structure through ousiometric fluctuations in cumulative word-time](https://mlsanity.com/paper/2208.09496/) (2022)
- [More Data Types More Problems: A Temporal Analysis of Complexity, Stability, and Sensitivity in Privacy Policies](https://mlsanity.com/paper/2302.08936/) (2023)

## Abstract (arXiv)

We explore the relationship between context and happiness scores in political tweets using word co-occurrence networks, where nodes in the network are the words, and the weight of an edge is the number of tweets in the corpus for which the two connected words co-occur. In particular, we consider tweets with hashtags #imwithher and #crookedhillary, both relating to Hillary Clinton's presidential bid in 2016. We then analyze the network properties in conjunction with the word scores by comparing with null models to separate the effects of the network structure and the score distribution. Neutral words are found to be dominant and most words, regardless of polarity, tend to co-occur with neutral words. We do not observe any score homophily among positive and negative words. However, when we perform network backboning, community detection results in word groupings with meaningful narratives, and the happiness scores of the words in each group correspond to its respective theme. Thus, although we observe no clear relationship between happiness scores and co-occurrence at the node or edge level, a community-centric approach can isolate themes of competing sentiments in a corpus.