Negative Interest Profiles for Social Media Content Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Social networking systems often present users with content that is of no interest due to the lack of effective methods to infer and filter out topics and information that users dislike, leading to a poor user experience.
Innovation Solution
A social networking system infers users' negative sentiments towards topics by analyzing interactions with other users, creating negative interest profiles to filter out unwanted content and improve content delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the social networking system presents content to users based on general interest matching, then content delivery volume is high, but user experience deteriorates due to presentation of unwanted content
Solution Approach 1:
The patent extracts and separates negative sentiment information from general user interactions. By creating a dedicated negative interest profile that specifically captures topics users dislike (through actions like page removals, unfriending, or explicit negative feedback), the system can filter out unwanted content while maintaining delivery of desired content, thus resolving the contradiction between high content delivery volume and user experience quality
Solution Approach 2:
The system implements feedback mechanisms where user interactions with content (particularly negative reactions, page removals, and unfriending actions) are continuously monitored and fed back into the negative interest profile. This feedback loop allows the system to dynamically adjust content delivery by learning from user responses, ensuring that unwanted content is progressively filtered while maintaining relevant content delivery
2Object-affected harmful factors
If the system filters content based on inferred negative sentiment, then user experience improves, but system complexity increases due to sentiment analysis requirements
Solution Approach 1:
The system enables users to self-serve by allowing them to explicitly indicate negative sentiments through actions such as removing pages, unfriending users, or expressing dislike. These self-provided signals are automatically captured and used to build the negative interest profile, eliminating the need for complex automated sentiment analysis while still achieving effective content filtering
Solution Approach 2:
The system performs preliminary classification of user actions to identify which interactions indicate negative sentiment. By pre-defining specific actions (page removals, unfriending, explicit negative feedback) as negative sentiment indicators, the system avoids the need for complex real-time sentiment analysis, thereby reducing system complexity while maintaining effective content filtering capability
3Productivity
If the system infers negative sentiment from user interactions, then content relevance improves, but information loss occurs about user's true preferences
Solution Approach 1:
The system uses explicit user feedback actions (such as removing pages, unfriending users, or direct negative reactions) as ground truth signals for negative preferences. These explicit feedback mechanisms ensure that the inferred negative sentiments accurately reflect user's true preferences, preventing information loss while improving content relevance through the negative interest profile
Data Source
AI summary
Users of a social networking system perform actions on various objects maintained by the social networking system. Some of these actions may indicate that the user has a negative sentiment for an object. To make use of this negative sentiment when providing content to the user, when the social networking system determines a user performs an action on an object, the social networking system identifies topics associated with the object and associates the negative sentiment with one or more of the topics. This association between one or more topics and negative sentiment may be used to decrease the likelihood that the social networking system presents content associated with a topic that is associated with a negative sentiment of the user.