Skip to main content
AIPromptIndex
ChatGPT Education intermediate

Research Source Evaluator and Citation Formatter

Added Sep 29, 2026

You are a university research librarian who teaches students to judge sources before they cite them. I am writing a [ASSIGNMENT] and want to use these sources to support this claim: [CLAIM] My sources, with every detail I have for each: [SOURCES] For each source, please: 1. Say what kind of source it is (peer-reviewed study, news report, reference work, opinion piece, or commercial content) and what that means for how much weight it can carry 2. State what the source shows, based on the details I gave, and whether that supports my claim as worded, supports only a weaker version, or does not support it 3. Flag the limits that matter for my claim: study design, what was actually measured, sample, date, or conflicts of interest 4. Format the citation in [CITATION_STYLE] using only the details I provided, marking any missing field as [missing: field] instead of inventing it Then: 5. Suggest a rewording of my claim that these sources can support 6. Tell me what kind of source I would need to support my original wording Do not add sources, page numbers, DOIs, or dates I did not give you. If you recognize a source and believe you know more about it, label that as something to verify against the source itself.
0
Share
Try in ChatGPT

About This Prompt

This prompt has ChatGPT check whether your sources support the claim you want to make before you cite them. For each source it identifies the type of source, states what it shows, and says whether it supports your claim as worded, only a weaker version, or not at all, flagging limits such as study design, what was measured, and sample. It formats each citation in the style you choose using only the details you supplied, marking missing fields instead of inventing them, then suggests a rewording of your claim that your sources can support and names the kind of evidence your original wording would need. It suits students writing research papers who want to avoid overclaiming and citation errors.

Variables to Customize

[ASSIGNMENT]

The assignment type and level

Example: first-year sociology research paper

[CLAIM]

The sentence you want your sources to support

Example: Heavy social media use causes depression in teenagers.

[SOURCES]

Each source with every citation detail you have and a note on what you took from it

Example: 1. Orben, Amy and Andrew K. Przybylski. "The association between adolescent well-being and digital technology use." Nature Human Behaviour, vol. 3, no. 2, 2019, pp. 173–182. DOI 10.1038/s41562-018-0506-1. My notes: three large datasets, over 355,000 adolescents; digital technology use explained at most 0.4% of the variation in well-being. 2. Twenge, Jean M. and W. Keith Campbell. "Associations between screen time and lower psychological well-being among children and adolescents: Evidence from a population-based study." Preventive Medicine Reports, vol. 12, 2018, pp. 271–283. DOI 10.1016/j.pmedr.2018.10.003. My notes: 2016 US survey of 40,337 children aged 2–17; 14- to 17-year-olds with 7+ hours of screen time a day were more than twice as likely to have been diagnosed with depression as those with 1 hour. 3. Wikipedia article "Screen time", no date or link saved.

[CITATION_STYLE]

The citation style your course requires

Example: APA 7th edition

Tips for Best Results

  • Include your own notes on what each source found. The prompt judges support from the details you give, so a bare citation gets a thinner evaluation.
  • Save the link and access date when you first find a source. Missing fields are the most common reason a citation cannot be completed later.
  • Check every formatted citation against your style guide or your library's citation page before submitting.

Example Output

**1. Orben & Przybylski (2019)**: peer-reviewed study of survey data, so it can show an association but not cause and effect. Supports your claim? No. The association it found was negative but small (at most 0.4% of the variation in well-being), and it measured digital technology use in general, not social media or depression specifically. It supports a weaker claim: technology use has at most a small association with lower well-being.
APA: Orben, A., & Przybylski, A. K. (2019). The association between adolescent well-being and digital technology use. *Nature Human Behaviour, 3*(2), 173–182. https://doi.org/10.1038/s41562-018-0506-1

**2. Twenge & Campbell (2018)**: peer-reviewed study of one national survey taken at a single point in time, so it cannot show whether heavy screen use or depression came first. Supports your claim? Only a weaker version: among 14- to 17-year-olds, very heavy screen time (7+ hours a day) is associated with a higher likelihood of a depression diagnosis. It measures all screen time, including TV and games, not social media alone.
APA: Twenge, J. M., & Campbell, W. K. (2018). Associations between screen time and lower psychological well-being among children and adolescents: Evidence from a population-based study. *Preventive Medicine Reports, 12*, 271–283. https://doi.org/10.1016/j.pmedr.2018.10.003

**3. Wikipedia, "Screen time"**: reference work that anyone can edit. Use it to find sources, then cite the studies it points to rather than the article itself.
APA: Screen time. ([missing: date of the page version you used]). In *Wikipedia*. [missing: link to that version]

**A claim your sources support:** "Very heavy screen time is associated with higher rates of depression diagnosis among older teenagers, although across large datasets the overall association between technology use and well-being is small."

**To support "causes":** a longitudinal study that follows the same teenagers over time, or an experiment that changes how much social media people use and measures depression afterwards.
research academic-writing critical-thinking citations source-evaluation

Get the Best AI Prompts Weekly

Curated prompts, tips, and guides delivered to your inbox every week. Free.

Subscribe free

Opens the Indexed newsletter. No spam — unsubscribe anytime.