Text analytics is all we do
Text carries insights. Rihlah extracts them.
Surveys, reports, transcripts, news coverage, reviews — your organization runs on words, and most are never analyzed. We build models to your question and turn that text into evidence you can act on — and defend.
Three Ways to Work With Us
Every engagement starts with a question and ends with validated findings. What varies is who brings the data — and how much of the work you want to own. Fixed scope, price agreed before work begins, and a deliverable you can hold us to.
You Collect. We Analyze.
You bring the corpus — survey responses, documents, transcripts, feedback, archives. We design the measurement and deliver findings.
- Measurement designed to your question — not a one-size-fits-all dashboard
- Models built and tuned for your text, applied at scale
- A findings report with a full methods appendix — every claim traceable to the text
- Sensitive data handled on infrastructure you approve
We Collect. We Analyze.
You have the question but not the data. We build the corpus — news coverage, public documents, the open web, multilingual sources — and run the analysis end to end.
- Corpus design: which sources, which period, which languages — and why
- Collection pipelines that run for a week or for years
- Tracking of themes, narratives, and attention over time — not just mention counts
- Recurring briefs and indicators, refreshed on the cadence you choose
You Upload. Our Models Analyze.
For teams that want analysis on demand: upload your text to the Rihlah analytics platform and get analyses generated by our trained text-analytics models.
- Built on the same models and methods we use in client engagements
- Auto-generated analyses in plain language — themes, patterns, and comparisons
- Onboarding and support from the people who built the models
- Access by subscription — ask us for a walkthrough
One-time study
A defined corpus, a defined question, a delivered answer — findings report, methods appendix, and a readout with your team.
Longitudinal contract
The same measurement, applied consistently over months or years — so you see change, not snapshots. Standing indicators, recurring briefs, and a series you can trust.
Also: Workshops & Training
Prefer to build the capability in-house? Our two-day text-analysis intensive — developed and taught at the university level — trains your team on your own data. No programming background required.
Not sure which fits? Tell us the question you’re trying to answer and we’ll point you to the right starting point — or tell you honestly that you don’t need us.
What’s in Your Text
A signal is anything in the words you can measure, compare, and track. A few of the questions text analytics answers:
Themes & topics
What are thousands of survey responses, reports, or comments actually about — and in what proportions? Which themes are growing, and which are new this quarter?
Framing & narratives
Not just whether an issue is mentioned, but how it’s portrayed — which frames dominate, how they differ across sources, and how they shift over time.
Claims, entities & quotes
Who is named, what is claimed, and who gets to speak — extracted from unstructured documents into clean, checkable tables.
Tone & emotion
Sentiment and emotion measured with validated instruments — not a black-box score — so a change in the number means a change in the world.
Attention & agendas
What a set of sources treats as important, who leads and who follows, and how attention moves — measured over time across outlets, channels, or languages.
Custom indicators
When the signal you need doesn’t have an off-the-shelf name, we define the construct, build the instrument, validate it, and report it on a schedule.
How an Engagement Runs
Text analytics isn’t feeding documents to a chatbot and pasting the answer. It’s measurement — and measurement has a discipline. Every engagement follows the same four moves.
Step 1
Define the question
A working session to turn “what’s in this text?” into something measurable: what counts, what doesn’t, and what a useful answer looks like.
Step 2
Build the instrument
We design the corpus and build the model for your question — the right method for the job, whether that’s a modern language model, a classic technique, or both.
Step 3
Run at scale
The instrument reads everything — thousands or millions of documents, in more than one language when needed — consistently, document by document.
Step 4
Validate & deliver
We check the machine against human judgment, report where it fails, and deliver findings with a methods appendix — so the analysis survives a skeptical board, editor, or reviewer.
Why Rihlah
AI made it easy to summarize text — and just as easy to be confidently wrong about it. The difference between a summary and a measurement is method. That is what we bring.
Research-Grade Methods
Led by Dr. Mohammad Yousuf — an award-winning professor who teaches computational text analysis and whose research on misinformation, media, and language technology has been cited more than 600 times and published in the world’s top computer-science venues.
A Journalist’s Skepticism
Eight years in national and international newsrooms taught our founder to verify before he trusts. Every model output — including AI’s — is held to the standard he learned on the copy desk: nothing is true until it’s verified.
A Builder’s Hands
We don’t resell someone else’s dashboard. We build the collection pipelines, the models, and the analyses ourselves — end to end — and hand them over documented, so what we build keeps working for you.
A Note on AI
Modern AI is the most powerful text-reading technology ever built, and we use it daily. But reading fast is not the same as measuring well: language models drift, miss, and confidently invent. That’s why every Rihlah analysis is validated against human judgment, reported with its limitations, and documented so it can be reproduced. Our founder researches these systems for a living and publishes on their failures as well as their strengths. When the answer matters — to a board, a funder, an editor, or a court — you deserve analysis that survives the question: how do you know?
Who We Work With
Any organization that runs on words — which is nearly every organization. If your decisions depend on what people wrote, said, published, or reported, we speak your language. For example:
Newsrooms & Media
Coverage analysis, audience feedback, and archives turned into stories, evidence, and strategy.
Education & Research
Open-ended surveys, program evaluations, and literature analyzed at a scale no team can read by hand.
Businesses
Customer feedback, service records, and market text turned into signals leadership can act on.
Nonprofits & Public Agencies
Community input, grantee reports, and public comments measured rigorously — and reported defensibly.
Not on this list? The industry matters less than the pattern: text you collect but never analyze, and decisions made without it. Tell us what you’re working on.
Funders, associations & program leads
We deliver analyses and training cohorts on behalf of foundations, associations, and program offices — one contract, many organizations served.
Multilingual corpora
Analysis doesn’t stop at English. We build and analyze corpora across languages — so international coverage, communities, and sources count too.
Based in Albuquerque — delivering across New Mexico, nationwide, and internationally.
Get Started
Five minutes, a few questions. Dr. Yousuf reads every submission personally and responds within two business days.