Note: OpenAI leads the general AI space, but AI companies are developing deep research tools and experimenting with AI-powered academic searching in support of research. Perhaps you have faculty or students asking you to present these tools to classes.
SciSpace is marketed as an AI-powered platform or "co-pilot" designed to assist researchers, students, and academics in streamlining their research and writing. The platform requires signing up for a profile, or using your Gmail account, which entitles you to one (1) free search; it then processes your request or question, and for further probing you'll need to pay for access.
SciSpace uses Semantic Scholar’s database with a proprietary combination of semantic and keyword search; features AI-generated summaries, paper recommendations, and a Chrome extension to enhance Google Scholar searching.
SciSpace aims to simplify literature reviews, paper analysis, and citation management with tools such as:
Semantic searching: query over 270 million papers using natural language to find relevant research with citations.
AI Copilot: analyzes PDFs, explains complex text, math, or tables; answers follow-up questions with citations.
Literature Review Tool: summarizes from multiple PDFs in a tabular format.
Citation Generator: supports 9,000+ styles (e.g., APA, MLA) with export options like BibTeX.
Paraphraser: rewords text in 75+ languages and 20+ tones for clarity and originality.
AI Detector: identifies AI-generated content in scholarly work.
PDF to Video: creates video abstracts from papers with AI narration.
Free access includes unlimited AI actions, PDF chats, and access to 1 million papers. Pay plans unlock advanced features such as AI co-editing.
Bottom line: For health sciences librarians, SciSpace might support their work with health professionals but its underlying AI raises concerns for those interested in scientific accuracy, transparency and rigour in reviews. Note information provided to you on this page is changing, so check the tool's website for the current information (or discuss with a librarian). Incidentally, I like to make a distinction between searching for sources and searching for answers. This much is true: LLMs provide the second while hiding the first.
Deep review feature
Deep Review is an AI-powered research assistant within SciSpace, designed to streamline systematic literature reviews by mimicking a researcher’s critical thinking. It aims to be a more precise alternative to ChatGPT’s Deep Research.
Query Input: Start with a general or specific research question (e.g., “Can AI-based personalized feedback enhance student engagement in higher education?”).
Intelligent Query Refinement: AI suggests more specific, context-aware questions to focus. Refine query through iterative prompts or submit directly.
Multi-Step Search: AI searches SciSpace’s database of over 280 million papers, analyzing abstracts, tracing citations, and identifying relevant papers. It uses natural language processing to understand context, not just keywords.
Result Synthesis: Delivers a list of papers (typically 20 from over 300 relevant ones) with summaries, organized in a user-friendly format. Users add custom columns to track specific variables across papers.
Transparency: Shows the steps of the search process, allowing users to verify the AI’s selections.
Presentation
Note: This presentation provides quick coverage of features; turn the sound down and read the captions. Also: as this is a marketing video and tutorial, some of the claims of the video should be tested and verified.
Librarian criticism
There are a range of issues with SciSpace unfortunately; high costs for subscriptions, and the customer service is not responsive. Technical issues are common (glitches, downtime, errors in processing), outdated literature (e.g., results skew towards pre-2015 papers). SciSpace operated somewhat smoothly early in my testing, but now runs into problems such as "502 Bad Gateway" errors. SciSpace embedded a custom GPT, and further issues arose such as unreliable results, inaccurate claims about papers, poor paraphrasing, and hallucinations (e.g., fabricating references or misinterpreting content). Users say it's fine for broad overviews not scholarly work. Try the free tier before purchasing.
"... This research evaluates the performance of platforms such as SciSpace, Elicit, ResearchRabbit, Scite.ai, Consensus, Claude.ai, ChatGPT, Google Gemini, Perplexity, and Microsoft Co-Pilot across the key stages of SLRs—planning, conducting, and reporting. While these tools significantly enhance workflow efficiency and accuracy, challenges remain, including variability in result quality, limited access to advanced features in free-tier versions, and the necessity for human oversight to validate outputs..."
Note: Please use your critical reading skills while reading entries. No warranties, implied or actual, are granted for any health or medical search or AI information obtained while using these pages. Check with your librarian for more contextual, accurate information.
