-- ThaisLobo - 03 Feb 2021

COVID-19 Conspiracy Books Ecologies: Mapping Discrepancies Across Amazon, Goodreads and Audible Routes to Problematic Content

Team members

Adinda Temminck, Amphy Feng, Erinne Paisley, Thais Lobo and Veronika Batzdorfer
Facilitators: Alex Gekker and Jonathan Gray

Summary of Key Findings

  • COVID-19 conspiracy books can be found across Amazon country marketplaces, but their availability and recommended products vary.
  • Even for books unavailable, Amazon and Audible recommendation affordances display other potential conspiracy books.
  • Amazon and GoodReads review affordances offer spaces that might entail conspiracy theorising;
  • GoodReads maintains a range of links to bookstores that offer buying options for customers of conspiracy books.
  • Linguistic markers (e.g. assessing the truth value of a proposition) offer nuanced views on users connected to potential conspiratorial ideation that are similar across GoodReads and Amazon.

Introduction

The COVID-19 pandemic brought to the public eye the role of digital platforms in sustaining access to the so-called infodemic, an explosion of unverified information related to the contingency of the virus that presents its own threats to public security. Under pressure to act, tech companies, such as Facebook, Instagram and Twitter, have suspended accounts linked to the spread of conspiracy theories like QAnon, 5G or ‘Save the Children' narrative.

Despite being part of the Big Five U.S. tech companies, along with Apple, Microsoft, Google and Facebook, Amazon has not been targeted with the same scrutiny of its counterparts in regards to the social interactions that it enables and fosters. As focus is now increasingly directed to less oversighted online spaces, Amazon started to take some actions in regards to some of the products and services it provides. A recent ban of merchandising QAnon-related products at the retailer's marketplaces follows the suspension of Parler platform from Amazon's backend cloud services in the aftermath of the U.S. Capitol invasion (Shieber, 2021).

In order to understand how certain conspiracies come to be/or are fused with other narratives, that is, the convergence of potential misinformation, it is important to investigate their presence in different platforms, particularly when users are enabled by recommendation algorithms to voice extreme views and/or are led to interact with problematic content in different ways. Therefore, in order to assess potential risks of platform design, it is crucial to integrate insights across platforms.

This project is part of a broader research initiative aiming to investigate the phenomenon of COVID-19 conspiracy theories in social media platforms. It investigates to what extent COVID-19 conspiracy books available at Amazon enable spaces for conspiracy theorising and which is their resonance in online conspiracy ecosystems. More specifically, this report explores the relation of books that potentially advance COVID-19 conspiracy theories and misinformation in the realm of Amazon and its subsidiary companies: (i) Amazon and its 19 country-specific marketplaces; (ii) Audible, an audiobook and podcast service; and (iii) Goodreads, a book cataloging website. Although these websites are not usually perceived as part of the same media group, they are all owned and operated by the Amazon conglomerate.The significance of recommendation algorithms of merchandising platforms, alongside the effectiveness and potential side effects of regulating measures to deplatform or deprioritze malicious content are not well understood and have not been sufficiently evaluated.

In this sense, this project aims to answer the following overarching research question: How does the Amazon owned websites potentially resonate online COVID-19 conspiracy theories?
The definition of a conspiracy theory, in this research, is understood as a knowledge production narrating a prominent catastrophic event, such as the pandemic, as an outcome of an orchestrated cover-up of events instead of the result of regular politics, chance or impersonal forces (Infodemic, 2020). Considering the hypothesis that there would be disparities across platforms, a comparative analysis was undertaken in order to explore (1) book availability, (2) recommendation features, and (3) users' discourses in reviews and recommendation practices.

Regarding the third research component, it's valuable to highlight that the detection of potential conspiratorial content poses a challenge in itself. When assessing possible conspiratorial argumentation, simple thematic keywords or derogatory language usage, taken alone, are insufficient to discriminate discourses, as different platform affordances and respective norms, temporal dynamics, external events or cultural norms pose confounding factors (van Prooijen & Douglas, 2018). Therefore, adopting a cross-platform view, as well as focusing on linguistic signals of user argumentation in context, offers more differentiated views on the role of such online communities in amplifying conspiracy content. Particularly, as semantic and pragmatic properties like markers of epistemic beliefs (e.g., “trust me”, “open your eyes”, “certainly”) indicate the individual attention, assessment of truth and commitment to stances (Humphreys & Wang, 2018) they offer views on user engagement that are less deterministic.

Initial Data Sets

A list of about 80 books potentially containing misinformation identified by researchers from the AHRC-funded Infodemic: Combatting COVID-19 Conspiracy Theories was used as a starting point of the research. The list was created by (1) collecting Amazon links mentioned in the video descriptions of YouTube conspiracy influencers and (2) by querying Amazon websites for COVID-19 related terms.

The titles were qualitatively analyzed to create a subset of n = 19 books with a narrower understanding of COVID-19 conspiracies. Skeptic books about COVID-19, vaccine or lockdown were not included. During the analysis, three more books were added to the subset, amounting for a total of 21 COVID-19 conspiracy books. Some additional COVID-19 skeptic books were also discovered but not included in the analyses related to book availability and recommendation features.

Text mining analysis was based on two datasets (Amazon books: n = 63 books and n = 587 user reviews; Goodreads: n = 12 books and n = 113 user reviews). Amazon's product details and reviews were crawled by the DMI winter school team with the scraper amazon-buddy (Nord, 2021), whereas Goodreads' reviews were crawled for similar books with rgoodreads (Votta, 2016). Both datasets comprise for instance textual data on user reviews, alongside metadata like date, user rating or rating of the review.

Research questions

RQ1. How does the Amazon owned websites resonate online COVID-19 conspiracy theories ecosystems?

RQ2. To what extent do user engagement practices, platform recommendation features and product availability differ among COVID-19 conspiracy theories books in Amazon, Goodreads, and Audible?

RQ3. Which conspiratorial ideation styles emerge through analysis of epistemic markers in users' reviews of conspiratorial books on Amazon and GoodReads?

Methodology

For the first analysis, a search for book titles was conducted on Amazon's 19 country stores, as each marketplace uses its own domain extension. Information regarding title availability was imputed into a spreadsheet. The process was repeated on GoodReads and Audible websites. The final graph enabled the comparison of availability between all platforms.
The second analysis consisted of a close reading of Amazon's recommendation features for the unavailable titles. A code system was created to match the page results shown after a search for the book titles. Five types of page results were retrieved through this analysis. The coding scheme goes as follows:
  1. No Results
  2. Sponsored Suggestions
  3. “Try these instead” algorithmically suggested
  4. “Did you mean” algorithmically suggested
  5. Results For…
The process was carried out in Amazon marketplaces and Audible (consisting only of type 1 and 3). GoodReads was excluded from this close reading as it was the only platform that contained all 20 books.

In the third analysis, all unavailable books categorised with page result type 3 were explored further. Screenshots were taken from the recommended books on Audible and Amazon. The screenshots were placed on a table. For Amazon, it was divided per country and per book. As for Audible, the screenshots were only per book. The results showed any common recommendations among Amazon’s national marketplaces and cross-platforms.

For the fourth analysis, the users’ usability on each platform was compared by listing each platform’s features. The features were listed and visualized in a table. The common features were rating, overall rating, and reviews. These features were used as a common denominator when further analyzing it per book. The next step was to indicate how different the rating, overall rating, and reviews were across platforms. Audible was excluded as no books were available.

The findings showed similar ratings on Amazon and GoodReads. Therefore, the next step was to closely read Amazon’s best-seller ranking. Each book’s best-seller ranking was noted, across 19 countries. The data was placed in a table, including what category the book received the best-seller ranking in and their position. The books that made up to the 50th position of thematic rankings were highlights.

As for the fifth and final analysis, the aim is to characterize and encode language use of users (e.g. summarise text features, word co-occurrences and word similarities) on both platforms Amazon and GoodReads. For this purpose, assumptions from distributional semantics are adopted, assuming that semantically similar words will co-occur in similar contexts (Firth, 1957). In this vein, individual words are embedded as dense vector representations whose distance (i.e., cosine similarity) indicates semantic similarity (Wang et al., 2020). Furthermore, based on a term co-occurrence matrix the probability which words co-occur is quantified with the positive pointwise mutual information measure as an association metric denoting the log ratio of the joint probability of two terms and their marginal probabilities (and further all PMI values < 0 are replaced with 0). That is, the positive value indicates words which co-occur more than expected by chance.

The following analysis steps have been implemented:
(i) Pre-processing of user review text for both platforms. This comprises separating review text in sequences of words (i.e., tokenizing), annotating text for their part of speech (e.g. proper noun, particle or adverb) and tagging the lemma of each word (e.g. words without inflections depending on the part of speech) as well as parsing their grammatical word dependencies. Pre-processing was conducted with the R-package udpipe 0.8.3 (Straka, & Straková, 2017).
 
(ii) Distributed representations. In order to explore word co-occurrences and semantic similarities, we leverage vector representations of words (i.e., Global Vectors for Word Representation [GloVe] (Pennington et al., 2014)). Essentially, the sequences of tokens are associated with numeric low-dimensional vectors (Chollet & Allaire, 2018). We used the Global Vectors for Word Representation embedding to capture the semantic similiartities between documents by leveraging the ratio of word co-occurence probabilities. These word embeddings were built with the text2vec 0.6 package (Selivanov & Wang, 2018), the lexvarsdatr package (Timm, 2019) as well as the tidyverse package (Wickham, 2017).

Findings

Finding 1: Availability (RQ1)

The conspiracy books availability varied across each Amazon 19 national marketplaces. Out of the 20 identified COVID-19 conspiracy books, six books were unavailable on all 19 national markets. All of them were available in GoodReads and none in Audible. Table 1 indicates with "x" unavailable books and with “eyes” the ones viewable on the websites.

An overall takeaway is that the availability of a book is independently determined by the platform. Despite Amazon being the parent company of Goodreads and Audible, the outcome of our research shows different results for all three platforms. This illustrates that each platform curates its policies towards conspiracy theory books differently.

Table 1. The availability of the books on Amazon’s 19 national marketplaces

Figure 1 shows the availability data sorted into a bar graph to illustrate the countries that have less available conspiracy books, on the left, compared to the countries that have the most available books, on the right. This ranking coincides with the general understanding of these countries' stances towards internet censorship (Bischoff, 2020). Sweden appears as an outlier because it does not as actively censor this type of content but may have fewer available books because of its unique approach to the COVID-19 pandemic (Molloy, 2020).

Figure 1. Amazon’s deplatforming of COVID-19 conspiracy books per country

The outcome of the varied Amazon national marketplace availability is not fully explained by Amazon's policies. Once a book is uploaded to an Amazon country website, a Kindle (digital) version of a book should be available across all Amazon country marketplaces (Chesson, 2020). For physical books, the uploader can select the desired “target region” for their book (e.g. Amazon Europe; Japan; Australia; North America) (Amazon Services, n.d.).

In both cases, distribution is dependent on publishing rights. However, as the Kindle Direct Publishing website states (Kindle Direct Publishing, n.d.), original unpublished content usually has worldwide rights. As it seems to be the case of the titles of our study, this factor may not fully explain discrepancies in availability across Amazon stores

Therefore, it is unknown if the books that are unavailable in specific Amazon country markets are inaccessible because the uploader chose to not list them in these regions, if Amazon actively removed them from these specific domains, if there are publishing rights restrictions involved, or if the algorithm for these Amazon domains does not encourage them to be listed. To answer this, further research and potential consultation with Amazon is required.

Regarding GoodReads book availability, the main finding is that the platform has available all the titles, including links to bookstores and spaces for user's reviews. Users can trace back to the original link of the book on Amazon as well as view other alternative online bookstores carrying the book, such as Barnes & Nobles and Book Depository.

Users who aren’t able to access the books on Amazon, thus use Goodreads as an outlet to express their concerns about the removal. The review section becomes an unmoderated space for users to share their inputs on the readings and alternative routes to access unavailable content.

Figure 2. Screenshot of a review on GoodReads, providing a free Kindle copy of a deplatformized book

Finding 2: Recommendation system (RQ2)

Although some conspiracy theory books were not available, Amazon's recommendation system displayed other conspiracy theory books for customers to purchase. By searching for unavailable books on different national Amazon stores, page results fitted into 5 categories. The first category has no results and additional information, the second category is sponsored recommendation, the third and fourth categories are automatically recommended books by the system, and the fifth category is related to products recommended by the system.

Figure 3 illustrates one of the books deplatformized on Amazon, The Great British Coronavirus Hoax: A Sceptics Guide, with category 3, “try these instead”, recommending another COVID-19 conspiracy book. Therefore, the removal of one COVID-19 conspiracy book may lead users to alternative options.

Figure 3. The deplatformized book ‘The Great British Coronavirus Hoax: A Sceptics Guide’ on Amazon with “Try these instead” algorithmically suggested

Through the analysis of the third and fourth categories, it was found that different countries have different system recommendation preferences. The title "The Great British Coronavirus Hoax: A Sceptics Guide" on Amazon in the U.S., for example, has different recommended categories from the ones that appear in countries like France, India and Spain. Image 3 shows that U.S. category recommendations revolve around "world" and "European" while in other national stores they are related to the title of the book, such as "British" and "coronavirus".

Figure 4. Book ‘The Great British Coronavirus Hoax: A Sceptics Guide’ on France, India, Spain and the US Amazon with different suggested categories

In the case of Audible platform, out of the 20 books, all of them unavailable, seven titles lead the user to a recommendation page. Most of the recommended problematic books had the QAnon conspiracy theory as the main subject. Similar to Amazon’s recommendation feature, conspiracy theory book unavailability on Audible does not diminish access to the titles, rather, it presents users with alternative problematic books.

Figure 5. Recommended alternatives for “Rises of the New World Order: Book Series Update and Urgent Status Report: Vol. 1" on Audible

Finding 3: Platform affordances (RQ2)

Despite Amazon owning Audible and Goodreads, each platform has its own affordances. As shown in Table 2, platforms have three similar affordances: rating, overall rating, and reviews. These features were taken into consideration when exploring how COVID-19 conspiracy books fostered conspiracy ecosystems.

Table 2. Platform features on Amazon, Audible, and GoodReads

The analysis has shown that 11 of the 20 books were listed in one or more of Amazon's best-seller categories, with some even listed above the #50th position. Table 3 shows that there are titles in #3 of 45-Minute Religion & Spirituality Short Reads, #5 of Business Planning & Forecasting, #6 of Contagious Diseases and #7 of Vaccinations categories.

The best-seller illustrates how popular the book is in a specific category but also portrays how legitimized it is in particular communities. Therefore, it exemplifies how conspiracy theories ecosystems are benefiting from Amazon's platform affordances.

Table 3. Books per position in Amazon's best-seller categories

Note. X= not included in the best-seller category. Star= Ranked above position #50.

Finding 4: Conspiratorial ideation styles and epistemic markers (RQ3)

When characterizing the nature of discussions on Amazon and GoodReads, with respect to indicators of epistemic beliefs comparable actors, actions and stances emerge. The co-occurrence network as well as Global Vectors for Word Representation i.e., GloVe embeddings for Amazon are based on n = 587 user reviews (comprising n = 46,811 lemmata) regarding n = 63 books. The following target terms of epistemic beliefs have been selected: ‘see’, ‘truth’ and ‘prove’, as well as more general concepts like ‘people’ and ‘vaccine’.

Based on the positive pointwise mutual information (PPMI) term-feature matrix these target terms are exemplified in a co-occurrence network (see Fig. 6) which show strong word associations between terms relating to truth propositions and causal assumptions (see Tab. 4).


Figure 6

Amazon Reviews Term Co-occurrence Network based on Term-feature Matrix  

Note. Node size indicates positive pointwise mutual information value (PPMI) between term and feature, node shapes indicate: triangle = target term, round shape = features. Target terms queried were ‘vaccine’, ‘people’, ‘prove’, ‘see’ and for each the 30 most associated terms. [Visualization with ggraph version 2.0.3 (Pedersen et al., 2017)]

Table 4

Example Target Terms from the PPMI-Term-feature matrix for Amazon reviews

Target term

Functional class

Example Features (PPMI)

'see'

Qualifiers of relevance and urgency

refreshing (4.74)

adequate (4.56)

pressure (4.90)

coming (5.03)

happening (3.97)

'vaccine'

Causal speech acts (entities and outcomes)

pharmaceutical (3.51)

proponents (3.83)

program (3.35)

gardasil (3.83)

consequences (3.39)

injury (3.81)

injured child (3.51)

ineffective (3.51)

killer vaccine (3.27)

'truth'

Truth propositions

truth reveals (4.34)

scam truth (3.62)

tell truth (5.23)

For the GloVe word embeddings 'see' returned the following terms with the highest cosine similarity: statistics (cos(θ) = 0.27), lingo dumb (cos(θ) = 0.26) or consensus scientific (cos(θ) = 0.27). For 'truth' the highest values for semantic similarity are dangerous (cos(θ) = 0.30), investigation (cos(θ) = 0.22), power (cos(θ) = 0.25), claims (cos(θ) = 0.211), silenced (cos(θ) = 0.20). Further, 'prove' returns the highest cosine values for nazis (cos(θ) = 0.24), search (cos(θ) = 0.24) or tell truth (cos(θ) = 0.26). For 'people' close terms returned are suffer (cos(θ) = 0.28), koehnlein (cos(θ) = 0.28) or admit (cos(θ) = 0.23) whereas, lastly, 'vaccine' is closely related to viral (cos(θ) = 0.28), inconvenient (cos(θ) = 0.25), democratic (cos(θ) = 0.31) or causes (cos(θ) = 0.24).

Regarding the co-occurrence network for GoodReads ’ reviews (see Fig. 7), it is based on n = 113 user reviews (with n = 30,298 lemmata) relating to n = 12 books. Indicators for assertions, conclusions and truth assumptions were: 'see', 'truth' and 'mainstream', 'hidden', as well as 'vaccine'. Example target terms from the PPMI term-feature matrix are shown below (see Tab. 5).

Figure 7

GoodReads Review Co-occurrence Network based on Term-feature Matrix

Note. Node size indicates positive pointwise mutual information value (PPMI) between term and feature, node shapes indicate: triangle = target term, round shape = features. Target terms queried were ‘vaccine’, ‘truth’, ‘mainstream’, ‘hidden’, ‘see’ and for each the 30 most associated terms. [Visualization with ggraph version 2.0.3 (Pedersen et al., 2017)]

Table 5

Example Target Terms from the Term-feature matrix for GoodReads reviews

Target term

Functional class

Example Features (PPMI)

'see'

Qualifiers of relevance and urgency

see happening (3.51)

see fail (4.29)

'vaccine'

Causal speech acts (entities and outcomes)

contains (3.16)

causes (2.89)

behind (3.16)

death (2.78)

dangerous (2.84)

propaganda vaccine (3.16)

'mainstream'

Entities

media mainstream (5.60)

narrative (5.89)

'truth'

Truth propositions

deeper truth (4.66)

'hidden'

Truth propositions

hidden behind (5.33)

decades hidden (5.06)

decades propaganda (4.83)

For the GloVe model 'see' appears close, in terms of cosine similarity, to read everyone (cos(θ) = 0.23), agree (cos(θ) = 0.23), one will (cos(θ) = 0.23). For 'truth' closely related are odds (cos(θ) = 0.30), embrace (cos(θ) = 0.26) or pharma (cos(θ) = 0.24). 'Mainstream' is related to program (cos(θ) = 0.28), murder (cos(θ) = 0.28), suggesting (cos(θ) = 0.25) or shame (cos(θ) = 0.25). 'Hidden' is semantically similar to book written (cos(θ) = 0.28), real (cos(θ) = 0.27), writing seriously (cos(θ) = 0.23) or long time (cos(θ) = 0.22). Lastly, 'vaccine' resembles subsidies (cos(θ) = 0.25), pains (cos(θ) = 0.25) or dont believe (cos(θ) = 0.22).

Visualizing term-feature relations of terms with related semantic meaning in the field of potential conspiratorial worldviews offers valuable insights on possible sources of these similarities and recurrent motives (e.g. the combination of entities like ‘mainstream media’, actions and outcomes e.g. death). It allows a focus on speech acts and social meaning construction making use of epistemic verbs like ‘see’ instead of being confined to predetermined literal topics and narratives and helps to understand interactions in a community culture. One of the main speech acts relates to the veracity aspect of information. In this argumentation mainstream media or proponents of vaccines are distorting and hiding information. As meaning construction depends on time, on the one hand dynamic word embeddings (e.g., RoBERTa) might prove to be a valuable future avenue, as they capture polysemy. On the other hand, the way respective books are received on other (fringe) platforms outside the Amazon sphere might offer even more differentiated views on a time lag in adoption as well as the significance and reach of sales platforms in the proliferation of potential conspiratorial worldviews.

Conclusion

From the research, it is possible to conclude that the unavailability of conspiracy theories books on Amazon does not fully diminish the accessibility to these and other problematic titles. Indeed, some of the platform affordances, such as recommendation features and users' reviews, serve the purpose of feeding users with alternative routes to conspiracy theory books even when the title of the original search is not available.

Additionally, discrepancies in availability across marketplaces and platforms do not encounter suitable explanations in Amazon's policy guidelines. Therefore, the lack of equitable and transparent moderation policies and practices may be argued as factoring in thespread of infodemic.

Further research on the role of Amazon as a social media company fostering potential conspiracy theorising could benefit from an analysis into the network of GoodReads concerning other bookstores it has affiliated with. Unlike Amazon's 19 national marketplaces, GoodReads does not adjust to the user’s location. Therefore, most of the reviews were written in English and published by users in English-speaking countries. In China, for example, Douban would be the alternative website for GoodReads. As mentioned, a bigger picture of COVID-19 conspiracy books online can be researched through a different angle by looking closely at each country as a case study.

References

Amazon Services. (n.d.). How to sell internationally with Amazon Global Selling. Retrieved from https://amzn.to/3pzv0aG

Bischoff, P. (2020, January 15). Internet Censorship 2020: A Global Map of Internet Restrictions. Comparitech. https://www.comparitech.com/blog/vpn-privacy/internet-censorship-map/

Chesson, D. (2020, November). Amazon International Markets Explained. Kindlepreneur. https://kindlepreneur.com/selling-kindle-books-internationally/.

Chollet, F., & Allaire, J.J. (2018). Deep learning for text and sequences. In Chollet F. & Allaire J.J.(Eds.), Deep learning with R. Manning. https://jjallaire.github.io/deep-learning-with-r-notebooks/notebooks/6.1-using-word-embeddings.nb.html

Firth, J. R. (1957). A synopsis of linguistic theory, 1930-1955. Studies in linguistic analysis.

Humphreys, A., & Wang, R. J. H. (2018). Automated text analysis for consumer research. Journal of Consumer Research, 44(6), 1274-1306. doi:10.1093/jcr/ucx104

Infodemic (2020, October 21). What are COVID-19 Conspiracy Theories? [Blog post] Retrieved from http://infodemic.eu/2020/10/21/what-are-covid-19-conspiracy-theories.html

Kindle Direct Publishing. (n.d.). Paperback Distribution Rights. Retrieved from: https://kdp.amazon.com/en_US/help/topic/G201834280

Molloy, S. (2020, May 3) Coronavirus: Inside Sweden’s unique and controversial approach to Covid-19. nzherald.co.nz. https://bit.ly/3owGc6I

Nord, A. (2021). Amazon Product Api. Amazon-buddy. 2.2.33. https://github.com/drawrowfly/amazon-product-api

Pedersen, T. L., Pedersen, M. T. L., LazyData, T. R. U. E., Rcpp, I., & Rcpp, L. (2017). Package ‘ggraph’.

Pennington, J., Socher, R., & Manning, C. D. (2014, October). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532-1543).

R Core Team. (2020). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. [Computer software].

Shieber, J. (2021, January 12). Amazon is removing products promoting the QAnon conspiracy. Techcrunch. https://techcrunch.com/2021/01/11/amazon-is-removing-products-promoting-the-qanon-conspiracy/

Votta, F. (2016). Package ‘rgoodreads’. https://github.com/Famguy/rgoodreads

Selivanov, D., & Wang, Q. (2018). Text2vec: Modern text mining framework for r. Retrieved from https://CRAN.R-project.org/package=text2vec

Straka, M., & Straková, J. (2017, August). Tokenizing, pos tagging, lemmatizing and parsing ud 2.0 with udpipe. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (pp. 88-99).

Timm, J. (2019). Package ‘textvardatr’. https://github.com/jaytimm/lexvarsdatr

van Prooijen, J. W., & Douglas, K. M. (2018). Belief in conspiracy theories: Basic principles of an emerging research domain. European journal of social psychology, 48(7), 897-908. doi:10.1002/ejsp.2530

Wang, Y., Hou, Y., Che, W., & Liu, T. (2020). From static to dynamic word representations: a survey. International Journal of Machine Learning and Cybernetics, 11, (pp. 1611-1630). doi:10.1007/s13042-020-01069-8

Wickham, H. (2017). The tidyverse. R package ver, 1(1), 1.
Topic revision: r6 - 19 Feb 2021, VeronikaBatzdorfer
This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Foswiki? Send feedback