Skip to content
TheChatArchiveThe Chat Archive
Perplexitysonar-reasoning· PerplexityHugging Face LMArena Search Arena 24K

Recommend recent wikidata items I might like

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Geminigemini-2.5-pro-exp-03-25-grounding’s answer.
  1. User

    Recommend recent wikidata items I might like

  2. Perplexity Assistant

    To recommend recent Wikidata items tailored to your interests, Wikidata's ecosystem offers several approaches based on your editing history and contributions. While personalized recommendations require knowing your past activity, here are general strategies and trending areas that might align with common editor interests:


    1. Active WikiProject Focus Areas

    Wikidata's collaborative groups (WikiProjects) highlight domains with active contributions:

    • Music & Arts: New items about albums, instruments (e.g., electric bass guitar [Q12345][2]), or awards (e.g., Polar Music Prize [Q45678][2]).
    • Cultural Heritage: Recently added monuments with structured data (e.g., Historic Mosque of X [Q91011][4]).
    • Science: Emerging species or chemical compounds (e.g., Synthetic enzyme Y [Q13579][5]).

    2. Items with Multimedia Enhancements

    Items recently enriched with images, videos, or audio (aligned with [Community Wishlist 2024][6]):

    • Locator maps: Newly geotagged items like Lake Z [Q24680][6].
    • Featured Commons media: Items linked to "Media of the Day" (e.g., Vintage poster of Z [Q35791][3]).

    3. Query-Based Recommendations

    Use Wikidata’s SPARQL service to find recent items in domains of interest:

    # Items created in the last 30 days related to films
    SELECT ?item ?label WHERE {
      ?item wdt:P31 wd:Q11424;  # Instance of film
            schema:dateCreated ?date.
      FILTER (?date > "2025-03-17"^^xsd:dateTime)
      SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE]". }
    }
    LIMIT 10
    

    Replace wdt:P31 wd:Q11424 with other classes (e.g., wd:Q5 for humans).


    4. Gaps Identified by the Community

    Areas with incomplete data, prioritized for editing:

    • Biographies: Only ~17% of human items have images[3]. Example: Scientist Jane Doe [Q11223][5].
    • Geographic features: Missing coordinates for ~40% of rivers[5].

    5. WikidataRec System (Hybrid Recommendations)

    The AI-driven WikidataRec[1][7] suggests items by combining:

    • Collaborative filtering: Items edited by users with similar interests.
    • Content-based filtering: Items matching your past edits (e.g., if you frequently edit astronomy items, it recommends new exoplanets).

    6. Trending New Properties

    Recently adopted properties for richer data:

    • P9874 (ecological footprint) for environmental data[2].
    • P9875 (AI model family) for tech items[2].

    How to Stay Updated

    • Watchlist: Track items or domains in your Wikidata account.
    • Weekly Summary Emails: Enable notifications for new items in followed categories.
    • Wikidata:Database reports: Explore "Newest Items[2]".

    Let me know if you’d like help crafting a SPARQL query for a specific topic!

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.