~/projects/general-conference
General Conference, Word by Word
What has been said from the pulpit of The Church of Jesus Christ of Latter-day Saints, and how it has changed? Every recorded General Conference talk from 1839 to 2026, 23.4M words by 1,063 speakers, in one searchable database, with a programme of unsupervised and supervised studies of the text and audio. The BYU devotionals and forums have a database of their own.
Sources: the Journal of Discourses for 1851–1886 (1,426 discourses, not all given at a conference), the printed Conference Report for 1880 and 1897–1941 (3,576 talks, split from the archive.org scans) and for 1942–1970 (1,824 talks, via BYU's Scripture Citation Index), and churchofjesuschrist.org for 1971 onward (3,978 talks). No Conference Report was printed for 1887–1896, and October 1957 is missing from the citation index.
Studies
Twenty-one studies of the corpus, each with its own data, method and interactive visuals, in the order they will ship. Studies that compare the two corpora live on one page linked from both hubs.
Guess the year
A model that dates a talk from its words alone, and the talks it gets most wrong: the ones ahead of or behind their time.
How phrases spread
New coinages such as “covenant path”, who adopted them and how fast, speaker by speaker and year by year.
The canon within the canon
A verse-level network of which scriptures are cited together, how central each verse is, and how that reweights by year.
Who quotes whom
Near-duplicate passages across every talk: recycled stories, self-quotation and how long a passage stays in circulation.
Who gets quoted
Every quotation classified as scripture, a prior leader, a secular author or personal, and the share of each over time.
What a paragraph does
Paragraphs tagged as doctrine, policy, exhortation, story or testimony, and the mix by era, calling and gender.
Who the talk is for
Predicting the session from the content, and where women's and priesthood sessions have converged.
What rose and what faded
Topic models by decade: the doctrines that rose, those that quietly faded, and whether BYU and conference drifted together.
How words changed meaning
Embeddings trained per era to measure how words like priesthood, family, gather and covenant moved.
Style fingerprints
Clustering speakers by style, and whether apostles' style converges after ordination.
The stories they tell
Narrative passages extracted, embedded and clustered into story families, from pioneer stories to global-member stories.
The shape of a talk
Whether a standard structure of a talk emerged, and when it hardened.
Whose talk is this
Predicting the speaker, then the calling, from the text, and which speakers the model confuses.
Which talks last
Predicting at delivery which talks are later reprinted, re-cited or added to curricula.
Which verse comes next
Given a paragraph, which scripture gets cited, and where leaders cite unexpectedly.
Responding to the world
Talks that answer an external event, and how many months the institution takes to respond.
How they sound
Pace, pauses and pitch range clustered across speakers, and whether voice clusters match text clusters.
Lost in translation
Where the official translations diverge most from the English, by language and over time.
What only Latter-day Saints say
Vocabulary that marks the Latter-day Saint pulpit against papal encyclicals, Spurgeon, Wesley and the presidents' inaugurals, and BYU against conference.
Every talk
Search and filter by year, session, speaker, title and the scripture a talk cites most. Open any talk for its length, reading grade and citations, with a link to the official page, or open a speaker for their whole record, their profile page and their entry in the leadership database. Filter by the calling held when speaking, resolved from the leadership records where the source prints only a title.
Sources & method
Talks from April 1971 onward come from the Church's own content API for churchofjesuschrist.org, with the byline, session, scripture links and official audio as published. Talks from April 1942 to October 1970 come from the printed Conference Report as transcribed by BYU's Scripture Citation Index, which also marks each scripture cited. Talks from April 1880 and from October 1897 to October 1941 come from the scanned Conference Report volumes on archive.org: the OCR text of each volume is split into talks at the printed speaker headers, the speaker's name is corrected against the mixed-case prose of the same volumes, and each talk links to its page in the scan. OCR errors remain in those texts, so their word counts and reading grades are approximate. The Journal of Discourses (1851–1886) comes from the transcription at jod.mrm.org; those sermons were given in many settings, not only at conference, and are dated by the discourse heading. Speakers are matched to the leadership database by name, keeping suffixes apart, so Brigham Young and Brigham Young Jr. are different people.
The texts are copyrighted by Intellectual Reserve, Inc. and their transcribers. This site stores the full text offline for analysis and publishes only metadata, aggregate measures and a single opening sentence per talk, with a link to the official page for the rest. Word counts exclude headings and footnotes. The reading grade is Flesch–Kincaid, computed on the prose. Scripture citations are the Church's own links where they exist and otherwise references written out in the text; citations without a chapter and verse are not counted.