You Get What You Chat: Using Conversations to Personalize Search-Based Recommendations

@article{Torbati2021YouGW,
  title={You Get What You Chat: Using Conversations to Personalize Search-Based Recommendations},
  author={Ghazaleh H. Torbati and Andrew Yates and Gerhard Weikum},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.04716}
}
Prior work on personalized recommendations has focused on exploiting explicit signals from user-specific queries, clicks, likes, and ratings. This paper investigates tapping into a different source of implicit signals of interests and tastes: online chats between users. The paper develops an expressive model and effective methods for personalizing search-based entity recommendations. User models derived from chats augment different methods for re-ranking entity answers for medium-grained… 

You Sound Like Someone Who Watches Drama Movies: Towards Predicting Movie Preferences from Conversational Interactions

The proposed method ConvExtr (Conversational Collaborative Filtering using External Data), which infers a user’s sentiment towards an entity from the conversation context, and transforms the ratings of “similar” external reviewers to predict the current user's preferences, can improve the accuracy of predicting users’ ratings for new movies by exploiting conversation content and external data.

Report on the Workshop on Personal Knowledge Graphs (PKG 2021) at AKBC 2021

The goal of the PKG’21 workshop was to create a forum for researchers and practitioners from diverse areas to present and discuss methods, tools, techniques, and experiences related to the construction and use of personal knowledge graphs, identify open questions, and create a shared research agenda.

Report on the 6th workshop on search-oriented conversational AI (SCAI 2021)

The 6th edition of the Search-Oriented Conversational AI workshop (SCAI 2021) was organised as a discussion platform on conversational AI for intelligent information access, bringing together researchers and practitioners across the fields of natural language processing, information retrieval, machine learning, and human-computer interaction.

References

SHOWING 1-10 OF 53 REFERENCES

Personalized Entity Search by Sparse and Scrutable User Profiles

This paper addresses personalization of book search, as an exemplary case of entity search, by exploiting sparse user profiles obtained through online questionnaires, and devise and compare a variety of re-ranking methods based on language models or neural learning.

Personalizing Search via Automated Analysis of Interests and Activities

This research suggests that rich representations of the user and the corpus are important for personalization, but that it is possible to approximate these representations and provide efficient client-side algorithms for personalizing search.

Personalised Reranking of Paper Recommendations Using Paper Content and User Behavior

This article examines an academic paper recommender that sends out paper recommendations in email newsletters, based on the users’ browsing history on the academic search engine, and proposes an approach to reranking candidate recommendations that utilizes both paper content and user behavior.

Conversational Recommendation: Formulation, Methods, and Evaluation

This tutorial covers four emerging directions of conversational recommender systems, providing a review of existing approaches and progress on the topic, and provides take-aways to practitioners to build their own systems.

Query Expansion with Enriched User Profiles for Personalized Search Utilizing Folksonomy Data

This work proposes a novel model to construct enriched user profiles with the help of an external corpus for personalized query expansion, and builds two novel query expansion techniques based on topical weights-enhanced word embeddings and topical relevance between the query and the terms inside a user profile.

Learning a Hierarchical Embedding Model for Personalized Product Search

The hierarchical embedding model is the first latent space model that jointly learns distributed representations for queries, products and users with a deep neural network and experiments show that it significantly outperforms existing product search baselines on multiple benchmark datasets.

To personalize or not to personalize: modeling queries with variation in user intent

Variation in user intent is examined using both explicit relevance judgments and large-scale log analysis of user behavior patterns to identify queries that can benefit from personalization.

The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation

It is demonstrated that UX design which enables people to preview the impact of their actions and highlights changes results in a higher reported transparency, an overall preference for this design, and a greater selectivity in which items are liked.

Probabilistic models for personalizing web search

This work proposes a generative model of relevance which can be used to infer the relevance of a document to a specific user for a search query, and shows how to learn these profiles from a user's long-term search history.

Transparent, Scrutable and Explainable User Models for Personalized Recommendation

This paper presents a new set-based recommendation technique that permits the user model to be explicitly presented to users in natural language, empowering users to understand recommendations made and improve the recommendations dynamically.
...