2020 Kaleidoscope

Deciphering Election News Patterns [Week 6, 11/22/2019]

SumUp Analytics

Nov 22· 3 min read

This newsletter is a weekly publication showcasing two simple applications of SumUp’s platform: an analysis of the news pertaining to the 2020 elections and a technical review of research published on computational linguistics.

2020 Election: Last week’s news coverage

What topics are most emphasized across the mainstream media’s coverage of the 2020 presidential election?

We ran 202 articles from 13 news feeds (in annex) through the SumUp platform. All information used is freely and easily available. We didn’t apply any filters. Keep in mind that these results are only representative of the 13 news sources listed at the bottom of this article.

This blog is not expressing an opinion but rather highlights the most relevant topics in the recent news coverage.

SumUp 2020 key topics on 11/22/2019, by order of relevance

Topic 1: Joe Biden/ Pete Buttigieg
Explanation: Not related to any specific theme, rather to a number of separate or combined occurrences, often concurrent to other candidates mentioned.

Topic 2: Donald Trump/ Impeachment inquiry
Explanation: Related to the coverage of the impeachment proceedings as well as the frequent mention in the last Democratic debate.

Topic 3: Republican primaries/Democratic primaries
Explanation: Related to various polls, in particular on the back of the last Democratic debate.

Topic 4: Trump Presidency/Deep Coup
Explanation: Related to President Trump mention of FBI spying on 2016 campaign.

Topic 5: Black voters/Democratic campaign
Explanation: Related to black voter support for Joe Biden and lack of support to Peter Buttigieg.

Topic 6: Health care
Explanation: Related to the last Democratic debate, health care proposals costs, availability of a public option, all part of the debate.

Topic 7: Bernie Sanders/Kamala Harris/ Amy Klobuchar/Cory Booker
Explanation: Related to their respective participation in the last Democratic debate and their participation in future events

Topic 8: Tulsi Gabbard
Explanation: Related to Gabbard’s exchange with Kamala Harris in the last democratic debate.

These topics are only representative of the key subjects appearing in the sources of information reviewed by Nucleus. A more refined interpretation, in terms of content or order of importance, is left to the reader and could easily be pursued with the Nucleus platform. In order to facilitate that analysis, we added the actual Nucleus analysis to the annex, providing further measure of sentiment attached to each of these topics, or a summary explanation of each topic.

Annex 1 Election 2020 news sources:
https://www.theguardian.com/us-news/us-elections-2020 https://fivethirtyeight.com/politics/elections/ https://www.chicagotribune.com/politics/elections/ https://www.politico.com/news/2020-elections https://www.cnn.com/specials/politics/2020-election-coverage https://time.com/5675691/2020-election-candidates-website-disability-accessibility/ https://www.newyorker.com/tag/2020-election https://www.foxnews.com/category/politics/2020-presidential-election https://www.usatoday.com/search/?q=2020%20democratic%20elections https://www.washingtonexaminer.com/tag/2020-elections https://www.washingtontimes.com/elections/ https://www.vox.com/2020-presidential-election https://www.breitbart.com/tag/2020-election/

Computational Linguistic Research Week of 11/22/2019

Leveraging its text analytics platform, SumUp has designed a simple method to rank recent research publications, purely based on their relation to the top topics extracted from these publications. Creating a corpus composed of all recent publications (all publications published on arxiv.org over the last week), Nucleus extracts 8 key topics representative of that research corpus. Nucleus then identifies the top documents related to these topics. SumUp ranks articles, according to the number of times each article is mentioned in the 8 extracted topics.

Using the corpus composed of articles published during the week of the 8th November 2019, the following 8 key topics are extracted:

[NLP/empirical methods][RNN/CNN][question answering/word embeddings][training data/language model][Deep learning/short term memory][learning rate/training set][social media/sexual violence][pre-trained language models]

Using SumUp ranking methodology, the following articles are most representative of the top 8 topics of the week of 11/22/2019:

Cantonese automatic speech recognition using transfer learning from mandarin Bryan Li, Xinyue Wang, Homayoon Beigi

[RNN/CNN] [training data/language model][learning rate/training set][pre-trained language models]

Improving document classification with multi-sense embeddings Vivek Gupta, Ankit Kumar, Pegah Nokhiz, Harshit Gupta, Partha Talukdar

[NLP/empirical methods] [RNN/CNN] [Deep learning/short term memory]

On using SpecAugment for end-to-end speech translation Parnia Bahar, Albert Zeyer, Ralf Schluter and Hermann Ney

[NLP/empirical methods] [RNN/CNN] [training data/language model]

A comparative study on end-to-end speech to text translation Parnia Bahar, Tobias Bieschke, and Hermann Ney

[NLP/empirical methods][RNN/CNN][training data/language model]

All of the other articles published during the period under review are individually less relevant to the top topics.