Understanding user interactions with podcast recommendations delivered via voice

Yang, Longqi; Sobolev, Michael; Tsangouri, Christina; Estrin, Deborah

doi:10.1145/3240323.3240389

Cited by 26 publications

(21 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DFT addresses both the choice context and the temporal dependency of choices. This directly matches the scenario in screen-based recommender systems where users browse items page by page and make decisions of action or not (note that in recently studied voice-driven recommender systems [7,16], this process however may not apply).…”

Section: Introductionsupporting

confidence: 64%

From preference into decision making

Zhao

Willemsen

Adomavicius

et al. 2019

Proceedings of the 13th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

User-system interaction in recommender systems involves three aspects: temporal browsing (viewing recommendation lists and/or searching/fltering), action (performing actions on recommended items, e.g., clicking, consuming) and inaction (neglecting or skipping recommended items). Modern recommenders build machine learning models from recordings of such user interaction with the system, and in doing so they commonly make certain assumptions (e.g., pairwise preference orders, independent or competitive probabilistic choices, etc.). In this paper, we set out to study the efects of these assumptions along three dimensions in eight diferent single models and three associated hybrid models on a user browsing data set collected from a real-world recommender system application. We further design a novel model based on recurrent neural networks and multi-task learning, inspired by Decision Field Theory, a model of human decision making. We report on precision, recall, and MAP, fnding that this new model outperforms the others. CCS CONCEPTS • Information systems → Recommender systems.

show abstract

Section: Introductionsupporting

confidence: 64%

From preference into decision making

Zhao

Willemsen

Adomavicius

et al. 2019

Proceedings of the 13th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

show abstract

“…The focal point of research efforts has been enabling the system to effectively and efficiently infer users' intents and satisfy their information needs [35,47]. Due to the complexity of the problem, it has been studied by several research communities including natural language processing [11,23,25], human-computer interaction [7,45], and information retrieval (including recommender systems) [8,44]. Existing work mainly takes a dialogue perspective with the goal of improving the question-answering process, i.e., asking the most relevant questions to collect user feedback.…”

Section: Voice-based Recommendationmentioning

confidence: 99%

“…A fundamental task in voice shopping is product recommendation, where the goal is to recommend relevant products to customers by inferring their preferences. While a growing body of research has addressed the voice-based recommendation problem from the dialogue perspective, i.e., improving the effectiveness of questionanswering between the customer and system [7,8,11,23,25,44,45], relatively little work has been focused on addressing the specific challenges arising in recommendation on Voice [40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Web-to-Voice Transfer for Product Recommendation on Voice

Zhang

Yang

2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

While product recommendation algorithms on the Web are wellsupported by a vast amount of interaction data, the same is not true on Voice. A promising approach to mitigate the issue is transfer learning, i.e., transferring the knowledge of customers' shopping behaviors learned from their shopping activities on the Web to Voice. Such a Web-to-Voice transfer is challenging due to customers' distinct shopping behaviors on Voice: customers are inclined to purchase more low-consideration products and are more likely to purchase certain products repeatedly. This paper presents TransV, a novel Web-to-Voice neural transfer network that allows for effective transfer of customers' shopping patterns from the Web to Voice, while taking into account customers' distinct purchase patterns on Voice. Our method extends the state-of-the-art self-attention neural architecture with a multi-level tri-factorization neural component, which allows to explicitly capture the similarity and dissimilarity of customers' shopping patterns on the Web and Voice. To model repeated purchases, TransV adopts a recency-based copy mechanism that considers the impact of the recency of historical purchases on customers' behavior of repeated purchases. Extensive validation on multiple real-world datasets, including two cross-platform datasets from Amazon.com and Amazon Alexa, shows that our method is able to improve voice-based recommendation substantially by 26.8% as compared with non-transfer learning methods. CCS CONCEPTS • Information systems → Recommender systems; • Computing methodologies → Transfer learning; Neural networks.

show abstract

“…We set out to construct features or representations that are predictive of non-textual podcast characteristics. End applications, such as recommendation engines [52], can then leverage these features as additional data inputs. This problem formulation is inspired by research in other content domains [47].…”

Section: Problem Formulation and Literature Reviewmentioning

confidence: 99%

More Than Just Words

Yang

Wang²,

Dunne

et al. 2019

Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed the flourishing of podcasts, a unique type of audio medium. Prior work on podcast content modeling focused on analyzing Automatic Speech Recognition outputs, which ignored vocal, musical, and conversational properties (e.g., energy, humor, and creativity) that uniquely characterize this medium. In this paper, we present an Adversarial Learning-based Podcast Representation (ALPR) that captures non-textual aspects of podcasts. Through extensive experiments on a large-scale podcast dataset (88,728 episodes from 18,433 channels), we show that (1) ALPR significantly outperforms the state-of-the-art features developed for music and speech in predicting the seriousness and energy of podcasts, and (2) incorporating ALPR significantly improves the performance of topic-based podcast-popularity prediction. Our experiments also reveal factors that correlate with podcast popularity.

show abstract

Understanding user interactions with podcast recommendations delivered via voice

Cited by 26 publications

References 21 publications

From preference into decision making

From preference into decision making

Web-to-Voice Transfer for Product Recommendation on Voice

More Than Just Words

Contact Info

Product

Resources

About