Podcasts have emerged as a massively consumed online content, notably due to wider accessibility of production means and scaled distribution through large streaming platforms. Categorization systems and information access technologies typically use topics as the primary way to organize or navigate podcast collections. However, annotating podcasts with topics is still quite problematic because the assigned editorial genres are broad, heterogeneous or misleading, or because of data challenges (e.g. short metadata text, noisy transcripts). Here, we assess the feasibility to discover relevant topics from podcast metadata, titles and descriptions, using topic modeling techniques for short text. We also propose a new strategy to leverage named entities (NEs), often present in podcast metadata, in a Non-negative Matrix Factorization (NMF) topic modeling framework. Our experiments on two existing datasets from Spotify and iTunes and Deezer, a new dataset from an online service providing a catalog of podcasts, show that our proposed document representation, NEiCE, leads to improved topic coherence over the baselines. We release the code for experimental reproducibility of the results.
Podcasts are traditionally shared through RSS feeds. As well as pointing to the audio files, RSS gives a creator a way of providing metadata about the podcast shows and episodes. We investigate how certain metadata fields associated with podcasts are currently being used and comment on their applicability to recommendations. Specifically, we find that many creators are not using the itunes:type field in the expected fashion, and that using this field for recommendations might not lead to an optimal user experience. We perform similar explorations for the season number and the category associat…
Rapidly growing online podcast archives contain diverse content on a wide range of topics. These archives form an important resource for entertainment and professional use, but their value can only be realized if users can rapidly and reliably locate content of interest. Search for relevant content can be based on metadata provided by content creators, but also on transcripts of the spoken content itself. Excavating relevant content from deep within these audio streams for diverse types of information needs requires varying the approach to systems prototyping. We describe a set of diverse podc…
A Bayesian approach to modeling topic-metadata relationships
Department of Statistics, Ludwig-Maximilians-Universität, Munich, Germany（1 统计系，路德维希-马克西米利安大学，慕尼黑，德国）；Department of Political Science, Ludwig-Maximilians-Universität, Munich, Germany（2 政治学系，路德维希-马克西米利安大学，慕尼黑，德国）
本文提出一种完全贝叶斯方法，通过用 Beta 回归替代线性回归并改进 R 包 stm 的合成法，更准确地量化主题与元数据关系的估计不确定性。
J.P. Morgan AI Research（摩根大通人工智能研究（J.P. Morgan AI Research））
Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems. This technique is not adequate when labeled examples are not available at training time and when the metadata artifacts in a document must be exploited. We address these challenges by generating document representations that capture both text and metadata artifacts in a task agnostic manner. Instead of traditional auto-regressive or auto-encoding based training, our novel self-supervised approach learns a soft-…
Podimo（波迪莫）；DTU Compute, Technical University of Denmark（丹麦技术大学计算学院）
For a multilingual podcast streaming service, it is critical to be able to deliver relevant content to all users independent of language. Podcast content relevance is conventionally determined using various metadata sources. However, with the increasing quality of speech recognition in many languages, utilizing automatic transcriptions to provide better content recommendations becomes possible. In this work, we explore the robustness of a Latent Dirichlet Allocation topic model when applied to transcripts created by an automatic speech recognition engine. Specifically, we explore how increasin…
Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）
Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been developed for particular applications, few are widely used in practice, as customization typically requires derivation of a custom inference algorithm. In this paper, we build on recent advances in variational inference methods and propose a general neural framework, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration…
This paper aims at an aspect sentiment model for aspect-based sentiment analysis (ABSA) focused on micro reviews. This task is important in order to understand short reviews majority of the users write, while existing topic models are targeted for expert-level long reviews with sufficient co-occurrence patterns to observe. Current methods on aggregating micro reviews using metadata information may not be effective as well due to metadata absence, topical heterogeneity, and cold start problems. To this end, we propose a model called Micro Aspect Sentiment Model (MicroASM). MicroASM is based on …
In this paper, we propose a deep, globally normalized topic model that incorporates structural relationships connecting documents in socially generated corpora, such as online forums. Our model (1) captures discursive interactions along observed reply links in addition to traditional topic information, and (2) incorporates latent distributed representations arranged in a deep architecture, which enables a GPU-based mean-field inference procedure that scales efficiently to large data. We apply our model to a new social media dataset consisting of 13M comments mined from the popular internet for…
To date, there have been massive Semi-Structured Documents (SSDs) during the evolution of the Internet. These SSDs contain both unstructured features (e.g., plain text) and metadata (e.g., tags). Most previous works focused on modeling the unstructured text, and recently, some other methods have been proposed to model the unstructured text with specific tags. To build a general model for SSDs remains an important problem in terms of both model fitness and efficiency. We propose a novel method to model the SSDs by a so-called Tag-Weighted Topic Model (TWTM). TWTM is a framework that leverages b…
ZBW—Leibniz Information Centre for Economics（ZBW—莱布尼茨经济信息中心）；Kiel University（基尔大学）
A significant part of the largest Knowledge Graph today, the Linked Open Data cloud, consists of metadata about documents such as publications, news reports, and other media articles. While the widespread access to the document metadata is a tremendous advancement, it is yet not so easy to assign semantic annotations and organize the documents along semantic concepts. Providing semantic annotations like concepts in SKOS thesauri is a classical research topic, but typically it is conducted on the full-text of the documents. For the first time, we offer a systematic comparison of classification …
Université de Lyon（里昂大学）；Lyon 2（里昂第二大学）；CNRS（法国国家科学研究中心）；CESI EXIA/LINEACT；UJM-Saint-Etienne（圣艾蒂安大学）；Lyon 1（里昂第一大学）
In the scientific digital libraries, some papers from different research communities can be described by community-dependent keywords even if they share a semantically similar topic. Articles that are not tagged with enough keyword variations are poorly indexed in any information retrieval system which limits potentially fruitful exchanges between scientific disciplines. In this paper, we introduce a novel experimentally designed pipeline for multi-label semantic-based tagging developed for open-access metadata digital libraries. The approach starts by learning from a standard scientific categ…
Although fully generative models have been successfully used to model the contents of text documents, they are often awkward to apply to combinations of text data and document metadata. In this paper we propose a Dirichlet-multinomial regression (DMR) topic model that includes a log-linear prior on document-topic distributions that is a function of observed features of the document, such as author, publication venue, references, and dates. We show that by selecting appropriate features, DMR topic models can meet or exceed the performance of several previously published topic models designed fo…
The Open University（开放大学）；Springer-Verlag GmbH（施普林格-费尔拉格有限责任公司）
Identifying the research topics that best describe the scope of a scientific publication is a crucial task for editors, in particular because the quality of these annotations determine how effectively users are able to discover the right content in online libraries. For this reason, Springer Nature, the world's largest academic book publisher, has traditionally entrusted this task to their most expert editors. These editors manually analyse all new books, possibly including hundreds of chapters, and produce a list of the most relevant topics. Hence, this process has traditionally been very exp…
Carnegie Mellon University（卡内基梅隆大学）；University of Technology Sydney（悉尼科技大学）；Tsinghua University（清华大学）；The University of Queensland（昆士兰大学）
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these videos are unsearchable by current search engines. Therefore, content-based video retrieval (CBVR) tackles this metadata-scarcity problem by directly analyzing the visual and audio streams of each video. CBVR encompasses multiple research topics, including low-level feature design, feature fusion, semantic detector training and video search/reranking…
Howard Hughes Medical Institute（霍华德·休斯医学研究所）；Northwestern University（西北大学）；Northwestern University Feinberg School of Medicine（西北大学范伯格医学院）；Rehabilitation Institute of Chicago（芝加哥康复研究所）
Much of human knowledge sits in large databases of unstructured text. Leveraging this knowledge requires algorithms that extract and record metadata on unstructured text documents. Assigning topics to documents will enable intelligent search, statistical characterization, and meaningful classification. Latent Dirichlet allocation (LDA) is the state-of-the-art in topic classification. Here, we perform a systematic theoretical and numerical analysis that demonstrates that current optimization techniques for LDA often yield results which are not accurate in inferring the most suitable model param…
