FLAME: A Probabilistic Model Combining Aspect Based Opinion Mining and Collaborative Filtering
By Yao Wu, Martin Ester. 2015
162 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Information Systems
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Information Systems
Citations in the corpus
- Explainable Recommendation: A Survey and New Perspectives (2018, background): “For example, Zhang et al. [2015b] attempted to leverage users’ time-sensitive interests on product aspects to explain the user purchasing behaviors, while based on memory networks, Chen et al.”
- Joint Deep Modeling of Users and Items Using Reviews for Recommendation (2017, background): “All competing techniques which are based on topic modeling [38, 3, 8] use the traditional bag of words techniques.”
- User Modeling with Neural Network for Review Rating Prediction (2015, background): “[Wu and Ester, 2015] leverage user information with a combination between collaborative filtering and aspect based opinion mining.”
- A Reinforcement Learning Framework for Explainable Recommendation (2018, methodology): “Pioneer embedded methods [7]–[9], [11] design explainable recommendation methods based on collaborative filtering.”
- Explainable Recommendation through Attentive Multi-View Learning (2019, background): “These works usually rely on shallow explainable components such as matrix factorization (Zhang et al. 2014a) and generative models (Diao et al. 2014; Wu and Ester 2015) for explanation generation.”
- Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources (2017, methodology): “Furthermore, [13, 39] proposed leveraging probabilistic graphical models to include more exible prior knowledge for review modeling.”
- Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews (2018, methodology): “Later on, most works attempt to extract latent topics or aspects from reviews automatically [2, 12, 17, 23, 26, 26, 31, 36, 39].”
- Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis (2015, background): “Fortunately, the ever developing phrase-level sentiment analysis techniques [18, 10, 36, 29] have made it possible to extract, summarize and structure the rich product features and user preferences automatically from free-text reviews, and have begun to be leveraged for personalized recommendation t”
- Explainable recommendation with fusion of aspect information (2018, background): “They explore user opinion [32, 35, 39, 40] from reviews by means of a sentiment lexicon [8, 36, 37] or corpus [14, 28, 44] and integrate these opinion information into recommendations.”
- Designing Explanation Interfaces for Transparency and Beyond (2019, background): “The key components were the research topics and the topical words of each research topic [25].”
- Personalized Reason Generation for Explainable Song Recommendation (2019, background): “The features can also be displayed in different forms [47–49].”
- Learning to Rank Features for Recommendation over Multiple Categories (2016, methodology): “For instance, if a user purchased a phone, and made a 5 star rating with the text review “screen is perfect, but earphone is bad!" The methods proposed in [17, 18] could capture the feature-sentiment pairs like (screen, perfect) and (earphone, bad), which would provide finer-grained analysis of the ”
- MMALFM (2018, background): “nually label reviews into different aspects, which requires expensive domain knowledge and high labor cost. Later on, most works attempt to extract latent topics or aspects from reviews automatically [2, 19, 29, 41, 45, 45, 56, 62, 63]. A general approach of these methods is to extract latent topics”