A recommendation system uses artificial intelligence to identify, based on negative sentiment cues from users, item attributes, such as keywords, that users may find offensive or undesirable. The negative sentiment cues may be explicit (e.g., a user selects an option not to view a particular recommendation again), implicit (e.g., a user does not interact with recommendations relating to an attribute), or both. The system may use a computer model generated based on these identified attributes to filter or modify recommendations to a user or group of users. For instance, if a particular keyword is identified as highly offensive to a group of users, items associated with the keyword may be filtered from item recommendations presented to the group of users. If an attribute is identified as moderately offensive to a user, items associated with the attribute may be down-weighted in item recommendations presented to the user.