This article will give you tips on how to analyze responses from a citizen survey about street lighting. You’ll learn practical approaches to survey analysis, deal with qualitative and quantitative data, and get more value from your survey responses.
Choosing the right tools for analyzing street lighting survey responses
If you want to make sense of citizen survey responses about street lighting, your approach depends on the structure and format of the data you’ve collected. Let me break it down by data type:
Quantitative data: Numbers are your friend here—things like “How many people feel unsafe after dark?” or “What percentage prefers LED lighting?” These questions suit classic tools like Excel and Google Sheets. You just need to count, filter, and maybe chart the numbers to spot trends.
Qualitative data: Open-ended responses or follow-up questions (“What would make you feel safer at night?”) are trickier. Manually reading hundreds of these is overwhelming and error-prone; reading all comments one by one just isn’t practical. That’s where AI tools shine, letting you analyze the meaning and patterns hidden in long texts.
There are two approaches for tooling when dealing with qualitative responses:
ChatGPT or similar GPT tool for AI analysis
Quick and accessible: If you have exported your survey responses, you can copy-paste data into ChatGPT or another general-purpose GPT tool. After that, you can prompt the AI with questions about the data (“What are citizens worried about concerning street lighting?”). This method is democratized—anyone can do it, but it’s not always convenient. Large data sets may hit input restrictions, formatting is finicky, and you often need to pre-process data to ensure it works well. Plus, you won’t have specialized analysis features tailored to surveys, so a lot falls on you to figure out the right prompts and interpret output.
All-in-one tool like Specific
Purpose-built for survey insights: All-in-one tools like Specific take the pain out of both collecting and analyzing qualitative feedback. You can launch conversational surveys (which makes it easier to collect detailed and focused responses since the AI asks smart follow-up questions). The analysis engine leverages generative AI to do the heavy lifting: instant summaries, surfacing hot topics and insights, and organizing all follow-up answers by question or theme.
Actionable insights, instantly: The chat interface means you can ask about themes, compare views—just like you might with ChatGPT—but with features that are survey-specific, such as managing which parts of the data the AI considers. With contextual filtering, high-quality followup collection, and structured organization, the work of extracting patterns, pain points, or positive feedback is straightforward. You spend less time wrangling spreadsheets and more time understanding what actually matters to your community.
Useful prompts that you can use to analyze citizen street lighting survey responses
Prompts are your toolkit when you want to interrogate survey response data with AI. Well-crafted prompts help AI surface actionable insights, group ideas, and spot themes. Here are some that work well—whether you’re trying to understand city safety perceptions or explore preferences for different kinds of street lighting:
Prompt for core ideas: This is the go-to starter—especially useful for large, unstructured datasets. It’s the backbone for getting a summary of what’s important to your respondents:
Your task is to extract core ideas in bold (4-5 words per core idea) + up to 2 sentence long explainer.
Output requirements:
- Avoid unnecessary details
- Specify how many people mentioned specific core idea (use numbers, not words), most mentioned on top
- no suggestions
- no indications
Example output:
1. **Core idea text:** explainer text
2. **Core idea text:** explainer text
3. **Core idea text:** explainer text
If you want to boost AI performance, always give it more context about the survey’s goal, audience, or situation. It helps the model “think” like you do when weighing responses. Here’s an example:
I collected these responses from a citizen survey on street lighting. My goal is to find out what worries or suggestions people raise about feeling safe after dark, as well as how people feel about different lighting technologies. Please extract themes and indicate the top concerns.
Dive deeper: After extracting themes, you can drill down by asking the AI to “Tell me more about [core idea],” exploring the nuance behind each topic.
Prompt for specific topic: When you want targeted validation (“Did anyone mention vandalism?”), try this:
Did anyone talk about [vandalism]? Include quotes.
Prompt for personas: Understand different groups in your city:
Based on the survey responses, identify and describe a list of distinct personas—similar to how "personas" are used in product management. For each persona, summarize their key characteristics, motivations, goals, and any relevant quotes or patterns observed in the conversations.
Prompt for pain points and challenges: Want to know what frustrates residents?
Analyze the survey responses and list the most common pain points, frustrations, or challenges mentioned. Summarize each, and note any patterns or frequency of occurrence.
Prompt for motivations & drivers: What drives respondents’ attitudes or suggestions?
From the survey conversations, extract the primary motivations, desires, or reasons participants express for their behaviors or choices. Group similar motivations together and provide supporting evidence from the data.
Prompt for sentiment analysis: Want a bird’s-eye view of how people feel?
Assess the overall sentiment expressed in the survey responses (e.g., positive, negative, neutral). Highlight key phrases or feedback that contribute to each sentiment category.
Want to get better at writing questions for surveys like this? Check out our deep-dive on the best citizen survey questions for street lighting.
How Specific summarizes and analyzes qualitative citizen survey responses by question type
The way responses are broken down and summarized in Specific depends on your question types:
Open-ended questions (with or without followups): The AI gives you a clean summary of all responses to that question, and if you’ve enabled followups, those answers are summarized in context—so, for example, you see not only “Why do you feel unsafe?” but also “What would make you feel safer?” in one place.
Choices with followups: For questions with multiple options (e.g., “What bothers you most at night?”) plus open-ended followups, each choice gets its own summary of citizen comments. That helps you compare viewpoints by group.
NPS questions: Each NPS segment (detractors, passives, promoters) gets its own qualitative analysis based on the followup answers, helping city officials dig into what drives satisfaction (or frustration) among each category of residents.
You can do all of this with ChatGPT or another general-purpose LLM, but it’ll mean a lot more copy-paste and manual filtering work on your end.
Learn more about AI-powered survey response analysis here, or explore our automatic AI followup feature for more info.
The challenge of AI context limits—and how to overcome them
If you’ve run a large citizen survey on street lighting, you’ll hit the problem of context limits—every AI model has a cutoff for how much data it can “see” at once. When you’ve got hundreds or thousands of detailed responses, that cap is easy to reach.
There are two main strategies for getting around this (and Specific offers both):
Filtering: You can filter conversations and focus analysis only on respondents who answered certain questions or made specific choices (say, “people who said the lighting is adequate”). This helps keep the dataset lean and relevant for the AI to process.
Cropping: Select just the questions you want the AI to focus on (e.g., open comments about LED bulbs or “other suggestions” fields). This trims the data so more conversations fit into context, which gives you higher-quality summaries.
These features allow you to run a detailed analysis across segment after segment, surfacing new insights without worrying about cutting important feedback out or overwhelming the model’s capacity.
Collaborative features for analyzing citizen survey responses
Anyone who’s ever worked on a citizen survey about street lighting—especially one with lots of open answers—knows that collaborating across teams or departments can get chaotic.
AI Chat for teamwork: In Specific, you analyze survey data just by chatting with AI—making it as natural as discussing insights over coffee. That means everyone involved, from city planners to community groups, can explore and ask questions, not just data analysts.
Multiple workspace chats: It supports multiple chats for the same dataset, each with its own filters (who replied, what they said, etc.). You always see the chat’s creator—so you know who’s exploring which themes—which is a gamechanger for collaborating with partners or tracking lines of inquiry.
Clear authorship and transparency: When collaborating with colleagues, each AI Chat message shows the sender’s profile. You always know who said what, so you can follow up or double-check findings.
This makes it easier than ever to build consensus, follow different trains of thought, and avoid messy, siloed spreadsheets. If you want a taste of what it’s like, check out our interactive citizen survey demos or try our AI survey generator for citizen street lighting surveys.
Create your citizen survey about street lighting now
Ready to uncover what citizens really think about street lighting? Create your survey easily, get better-quality responses with conversational AI, and turn feedback into insights—no more tedious manual analysis needed.