content_analysis_summary
Analyze keyword citation data to extract insights on sentiment, connotation, and page types using targeted filters. Enhance SEO strategies with detailed content analysis summaries.
Instructions
This endpoint will provide you with an overview of citation data available for the target keyword
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| initial_dataset_filters | No | initial dataset filtering parameters initial filtering parameters that apply to fields in the Search endpoint; you can add several filters at once (8 filters maximum); you should set a logical operator and, or between the conditions; the following operators are supported: regex, not_regex, <, <=, >, >=, =, <>, in, not_in, like,not_like, has, has_not, match, not_match you can use the % operator with like and not_like to match any string of zero or more characters; example: ["domain","<>", "logitech.com"] [["domain","<>","logitech.com"],"and",["content_info.connotation_types.negative",">",1000]] [["domain","<>","logitech.com"]], "and", [["content_info.connotation_types.negative",">",1000], "or", ["content_info.text_category","has",10994]] | |
| internal_list_limit | No | maximum number of elements within internal arrays you can use this field to limit the number of elements within the following arrays | |
| keyword | Yes | target keyword Note: to match an exact phrase instead of a stand-alone keyword, use double quotes and backslashes; | |
| keyword_fields | No | target keyword fields and target keywords use this parameter to filter the dataset by keywords that certain fields should contain; you can indicate several fields; Note: to match an exact phrase instead of a stand-alone keyword, use double quotes and backslashes; example: { "snippet": "\"logitech mouse\"", "main_title": "sale" } | |
| page_type | No | target page types | |
| positive_connotation_threshold | No | positive connotation threshold specified as the probability index threshold for positive sentiment related to the citation content if you specify this field, connotation_types object in the response will only contain data on citations with positive sentiment probability more than or equal to the specified value | |
| sentiments_connotation_threshold | No | sentiment connotation threshold specified as the probability index threshold for sentiment connotations related to the citation content if you specify this field, sentiment_connotations object in the response will only contain data on citations where the probability per each sentiment is more than or equal to the specified value |
Implementation Reference
- The `handle` method in `ContentAnalysisSummaryTool` executes the core tool logic by constructing parameters and making a POST request to the DataForSEO `/v3/content_analysis/summary/live` endpoint, then formatting the response.async handle(params: any): Promise<any> { try { const response = await this.dataForSEOClient.makeRequest('/v3/content_analysis/summary/live', 'POST', [{ keyword: params.keyword, keyword_fields: params.keyword_fields, page_type: params.page_type, initial_dataset_filters: this.formatFilters(params.initial_dataset_filters), positive_connotation_threshold: params.positive_connotation_threshold, sentiments_connotation_threshold: params.sentiments_connotation_threshold, internal_list_limit: params.internal_list_limit }]); return this.validateAndFormatResponse(response); } catch (error) { return this.formatErrorResponse(error); } }
- The `getParams` method defines the Zod schema for input parameters to the tool, including keyword, filters, thresholds, etc.getParams(): z.ZodRawShape { return { keyword: z.string().describe(`target keyword Note: to match an exact phrase instead of a stand-alone keyword, use double quotes and backslashes;`), keyword_fields: z.object({ title: z.string().optional(), main_title: z.string().optional(), previous_title: z.string().optional(), snippet: z.string().optional() }).optional().describe( `target keyword fields and target keywords use this parameter to filter the dataset by keywords that certain fields should contain; you can indicate several fields; Note: to match an exact phrase instead of a stand-alone keyword, use double quotes and backslashes; example: { "snippet": "\\"logitech mouse\\"", "main_title": "sale" }` ), page_type: z.array(z.enum(['ecommerce','news','blogs', 'message-boards','organization'])).optional().describe(`target page types`), initial_dataset_filters: z.array( z.union([ z.array(z.union([z.string(), z.number(), z.boolean()])).length(3), z.enum(["and", "or"]) ]) ).max(8).optional().describe( `initial dataset filtering parameters initial filtering parameters that apply to fields in the Search endpoint; you can add several filters at once (8 filters maximum); you should set a logical operator and, or between the conditions; the following operators are supported: regex, not_regex, <, <=, >, >=, =, <>, in, not_in, like,not_like, has, has_not, match, not_match you can use the % operator with like and not_like to match any string of zero or more characters; example: ["domain","<>", "logitech.com"] [["domain","<>","logitech.com"],"and",["content_info.connotation_types.negative",">",1000]] [["domain","<>","logitech.com"]], "and", [["content_info.connotation_types.negative",">",1000], "or", ["content_info.text_category","has",10994]]` ), positive_connotation_threshold: z.number() .describe(`positive connotation threshold specified as the probability index threshold for positive sentiment related to the citation content if you specify this field, connotation_types object in the response will only contain data on citations with positive sentiment probability more than or equal to the specified value`).min(0).max(1).optional().default(0.4), sentiments_connotation_threshold: z.number() .describe(`sentiment connotation threshold specified as the probability index threshold for sentiment connotations related to the citation content if you specify this field, sentiment_connotations object in the response will only contain data on citations where the probability per each sentiment is more than or equal to the specified value`) .min(0).max(1).optional().default(0.4), internal_list_limit: z.number().min(1).max(20).default(1) .describe( `maximum number of elements within internal arrays you can use this field to limit the number of elements within the following arrays`) .optional(), }; }
- In `ContentAnalysisApiModule.getTools()`, the `ContentAnalysisSummaryTool` is instantiated and registered into the module's tools map using its name as key.getTools(): Record<string, ToolDefinition> { const tools = [ new ContentAnalysisSearchTool(this.dataForSEOClient), new ContentAnalysisSummaryTool(this.dataForSEOClient), new ContentAnalysisPhraseTrendsTool(this.dataForSEOClient), // Add more tools here ]; return tools.reduce((acc, tool) => ({ ...acc, [tool.getName()]: { description: tool.getDescription(), params: tool.getParams(), handler: (params: any) => tool.handle(params), }, }), {}); }
- src/core/utils/module-loader.ts:38-40 (registration)In `ModuleLoaderService.loadModules()`, the `ContentAnalysisApiModule` (which provides the content_analysis_summary tool) is conditionally instantiated and added to the list of modules if 'CONTENT_ANALYSIS' is enabled.if(isModuleEnabled('CONTENT_ANALYSIS', enabledModules)) { modules.push(new ContentAnalysisApiModule(dataForSEOClient)); }