Step 5 · Zotero, PDFs and Export

Select the corpus from both pools by four routes, file it in Zotero, choose the works to read in full and collect their PDFs, merge the duplicates, and export the library as files an analysis can read.

Part 1 · Step 5 of Steps 0–5
Output · an exported corpus of 1,261 works, 434 for full reading and 309 with a full text

Steps 3 and 4 leave two scored pools, one from the searches and one from the citations. This step turns them into the corpus. The selection is made by rules the researcher approves, the filing is done by the agent, and collecting PDFs from licensed publisher sites is done by a person with the agent's help. The step ends with an export, so that the analysis in Literature Review II reads fixed files rather than a library that keeps changing.

Section 1Four routes into the corpus

A single score favours one kind of work. The worked example therefore selected by four routes, each with its own rule, over the keyword pool of 19,186 candidates and the citation pool of 3,684 cited works, 3,481 of them distinct from the keyword pool. A work enters the corpus if any route selects it.

Table 5.1Selection routes and the works each selected
RouteRuleWorks
Text relevancecombined score of at least 0.85, with an abstract486
Seed citationcited by at least two sources, or by a reference document and one other source151
Field influencetop 10% by citations per year, passing a topic check89
Discovery convergencetop 10% by discovery signal, passing a topic check347
Any routethe Expanded cut1,038
From 16_select-articles. The routes overlap, so the union is smaller than the sum.
What each route catches

Text relevance finds works that read like the seeds. Seed citation finds the works the seeds rely on, however little metadata they have. Field influence finds widely cited works that the seeds happen not to cite. Discovery convergence finds works that many different searches lead to. Each route alone would leave a recognisable gap.

Section 2Two cuts

Not every work in the corpus needs to be read in full. The researcher confirmed two cuts. The Expanded cut of 1,038 works, confirmed on 13 October 2026, is the corpus read by title and abstract. The PDFs cut, confirmed on 15 October 2026, is the part to be read in full. It held 300 works, 292 chosen by rule and 8 added by the researcher.

Section 3Filing in Zotero

The agent created the Zotero records through the web API, all 1,038 of the Expanded cut in 2 Expanded / Standard Platforms with none failing, and tagged each with the searches that found it. It then filed the PDFs cut in 3 PDFs / Standard Platforms, 298 works once two book reviews had been dropped. Because an item can sit in both collections, nothing is copied.

Table 5.2Country tags on the imported records
TagRecords
China399
North Korea242
Vietnam119
A record carries the tag of every country search that found it.
Figure 5.1A record filed by the agent
Zotero desktop with the item A dictator's retort to economic sanctions, Evidence from North Korea, selected in 3 PDFs, Standard Platforms. The Info pane shows a journal article by Youngseok Park in the European Journal of Political Economy, dated 2025-09-01, volume 89.
The Info pane shows the metadata the agent wrote from the open-index record.

Section 4Collecting the PDFs

PDFs come from publisher sites, and most publishers license them to a university rather than to the public. The agent searched each record in the NCCU library catalogue and built a local page of links that go through the library proxy to the publisher's own page for the article. A person signed in to the library opens each link and saves the article with the Zotero Connector, which stores the record, a snapshot of the page and the PDF together.

Figure 5.2A publisher page opened through the library
ScienceDirect page for the open-access article From marketization to a market economy in North Korea by Byung-Yeon Kim, in Asia and the Global Economy, July 2022, with a View PDF button and the DOI 10.1016/j.aglobe.2022.100038. The header shows access through National Chengchi University.
The publisher link for this record opened the article page on ScienceDirect, signed in through NCCU.
Figure 5.3Saving with the Zotero Connector
The Zotero Connector popup over the same ScienceDirect page, saving to the collection Standard Platforms under 2026.10 Post-Socialist Transformation, 3 PDFs. The popup lists the item with a ScienceDirect Snapshot and a ScienceDirect Full Text PDF.
Choose the collection in the Connector before saving, and wait until the PDF has been saved before clicking Done.
Figure 5.4The saved attachments
Zotero desktop with the Attachments pane of a selected item showing two attachments, ScienceDirect Full Text PDF and ScienceDirect Snapshot.
After a Connector save the item carries the full-text PDF and a snapshot of the publisher page.

The link page was rebuilt as PDFs came in and records were merged. Its last run, on 12 November 2026, covered the records in 3 PDFs / Standard Platforms that still had no PDF. An English example with real records and inactive links is on the example publisher-links page.

Table 5.3The last publisher-link run
OutcomeRecords
Records without a PDF, searched in the NCCU library123
Found in the library25
with a publisher link6
with no publisher link among the online options19
Not found in the library98
From 40_publisher-links. The six publisher links were on Taylor & Francis (2), Elsevier, Wiley, SAGE and Oxford.
PDFs behind a login stay with a person

Publisher licences generally forbid systematic downloading, and many sites show a verification page to automated browsers. The agent never signs in, never solves a verification page and never downloads in bulk from a licensed site. It prepares the links, and a person with library access does the saving.

Section 5Merging duplicates

Every Connector save creates a new record beside the one the agent filed, and seeds, captures and search results can describe the same work in different ways. The agent audits the collections, finds records that describe the same work, and merges each set into one record. In the worked example one collection audit merged 62 sets of duplicates, and a later pass over the Chinese seeds merged 33 more.

Section 6Exporting the corpus

The export reads the Zotero collections 2 Expanded and 3 PDFs and writes each to a folder of the same name in the review folder. The PDFs folder also receives the PDF files and a plain-text version of each, which is what the analysis reads. Each run is recorded in its own step folder and in a changelog.

Table 5.4Export history of the worked example
Export2 Expanded, works3 PDFs, works3 PDFs, with a PDF
24 October 20261,280458315
26 October 20261,270442313
27 October 2026 (v2.3)1,261434309
11 November 2026 (v2.4)1,259433309
From the export histories in the README of each folder. The collections grew after the import of 15 October as seeds and works added by the researcher were filed in them, and shrank at each export as duplicates were merged.

Literature Review II reads the export of 27 October 2026, version 2.3, with 1,261 works in the expanded corpus and 434 in the PDFs corpus, 309 of them with a full text. Its analysis guide was written from the export of 26 October, with 1,270 and 442 works, and the duplicate merges of 27 October then reduced the counts to those of version 2.3. A further merge produced version 2.4 on 11 November 2026, two works smaller, which does not change the analysis.

  • citation_index.csvOne row per work, with creators, date, venue, identifiers, abstract and tags.both folders
  • corpus_manifest.csvOne row per work, with its PDF status and main PDF.both folders
  • citations.risThe whole collection in RIS, for Zotero, EndNote or Mendeley.both folders
  • scores.csvThe scores and selection routes of each work, from Steps 3 to 5.2 Expanded Corpus
  • pdfs/ and text/The PDF files and a plain-text version of each, with a text manifest.3 PDFs
  • corpus_changelog.jsonlOne line per export run.both folders

Terminology

Selection route
A rule that admits works to the corpus by one kind of evidence, such as text similarity or citation by the seeds.
Expanded cut
The full selected corpus, read by title and abstract.
PDFs cut
The part of the corpus chosen for full reading, for which PDFs are collected.
Library proxy
A university service that lets a signed-in member open licensed publisher sites from off campus.
Zotero Connector
The browser extension that saves the article on the current page, with its PDF, into a chosen Zotero collection.
Export
A fixed copy of a Zotero collection as files, recorded with its date, so that an analysis can cite the exact version it read.