User-specific Interests Research Articles

Machine Learning System Implementation of Education Podcast Recommendations on Spotify Applications Using Content-Based Filtering and TF-IDF

Spotify, this popular music and podcast streaming service, has a fundamental problem in assisting clients in finding podcasts that fit their interests. Thus, the goal of this project is to develop a podcast recommendation system that would enhance users' capacity to identify pertinent content, particularly in the educational genre. By using content-based filtration techniques, this system analyzes the user's listening preferences and interests before recommending educational podcasts. The podcast data source is Spotify, and the suggestions are produced using the TF-IDF and Cosine Similarity techniques. The recommendations provide a list of educational podcasts catered to the user's specific interests. The Confusion Matrix Classification Report was tested to assess system performance during the review phase. Precision values show how accurate the system was at recommending educational podcasts; on average, they range from 0.52 to 0.74. Additionally, the recall value showed a mean of 0.51 and a mean of 0.79, indicating that the algorithm successfully located the relevant content. To put it briefly, this custom recommendation engine enhances the listening experience for Spotify customers by suggesting educational podcasts based on their preferences. The system's ability to match users with material that aligns with their interests was demonstrated by the metrics used to assess its performance. With more user interactions with the system, it was anticipated by Cosine Similarity, a statistic used to determine the quality of recommendations, will continue to improve. To improve user experience and personalize the podcast listening experience on Spotify, this research addresses the challenge of locating suitable podcasts.

CERC: an interactive content extraction, recognition, and construction tool for clinical and biomedical text

BackgroundAutomated summarization of scientific literature and patient records is essential for enhancing clinical decision-making and facilitating precision medicine. Most existing summarization methods are based on single indicators of relevance, offer limited capabilities for information visualization, and do not account for user specific interests. In this work, we develop an interactive content extraction, recognition, and construction system (CERC) that combines machine learning and visualization techniques with domain knowledge for highlighting and extracting salient information from clinical and biomedical text.MethodsA novel sentence-ranking framework multi indicator text summarization, MINTS, is developed for extractive summarization. MINTS uses random forests and multiple indicators of importance for relevance evaluation and ranking of sentences. Indicative summarization is performed using weighted term frequency-inverse document frequency scores of over-represented domain-specific terms. A controlled vocabulary dictionary generated using MeSH, SNOMED-CT, and PubTator is used for determining relevant terms. 35 full-text CRAFT articles were used as the training set. The performance of the MINTS algorithm is evaluated on a test set consisting of the remaining 32 full-text CRAFT articles and 30 clinical case reports using the ROUGE toolkit.ResultsThe random forests model classified sentences as “good” or “bad” with 87.5% accuracy on the test set. Summarization results from the MINTS algorithm achieved higher ROUGE-1, ROUGE-2, and ROUGE-SU4 scores when compared to methods based on single indicators such as term frequency distribution, position, eigenvector centrality (LexRank), and random selection, p < 0.01. The automatic language translator and the customizable information extraction and pre-processing pipeline for EHR demonstrate that CERC can readily be incorporated within clinical decision support systems to improve quality of care and assist in data-driven and evidence-based informed decision making for direct patient care.ConclusionsWe have developed a web-based summarization and visualization tool, CERC (https://newton.isye.gatech.edu/CERC1/), for extracting salient information from clinical and biomedical text. The system ranks sentences by relevance and includes features that can facilitate early detection of medical risks in a clinical setting. The interactive interface allows users to filter content and edit/save summaries. The evaluation results on two test corpuses show that the newly developed MINTS algorithm outperforms methods based on single characteristics of importance.

Simultaneous change region and pattern identification for very high-resolution images

By taking advantages of fine details obtained by the improved spatial resolution, very high-resolution images are promising for detecting change regions and identifying change patterns. However, high overlaps between different change patterns and the complexities of multiclass classification make it difficult to reliably separate change features. A framework named simultaneous change region and pattern identification (SCRAPI) is proposed for simultaneously detecting change regions and identifying change patterns, whose components are aimed at capturing overlaps between change patterns and reducing overlaps driven by user-specific interests. To validate the effectiveness of SCRAPI, a supervised approach is illustrated within this framework, which starts with modeling the relationship between change features by interclass couples and intraclass couples, followed by metric learning where structural sparsity is captured by the mixed norm. Experiments demonstrate the effectiveness of the proposed approach. (C) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)

Self-organizing flows in social networks

Social networks offer users new means of accessing information, essentially relying on “social filtering”, i.e. propagation and filtering of information by social contacts. The sheer amount of data flowing in these networks, combined with the limited budget of attention of each user, makes it difficult to ensure that social filtering brings relevant content to interested users. Our motivation in this paper is to measure to what extent self-organization of a social network results in efficient social filtering.To this end we introduce flow games, a simple abstraction that models network formation under selfish dynamics, featuring user-specific interests and budget of attention. In the context of homogeneous user interests, we show that selfish dynamics converge to a stable network structure (namely a pure Nash equilibrium) with close-to-optimal information dissemination. We show that, in contrast, for the more realistic case of heterogeneous interests, selfish dynamics may lead to information dissemination that can be arbitrarily inefficient, as captured by an unbounded “price of anarchy”.Nevertheless the situation differs when user interests exhibit a particular structure, captured by a metric space with low doubling dimension. In that case, natural autonomous dynamics converge to a stable configuration. Moreover, users obtain all the information of interest to them in the corresponding dissemination, provided their budget of attention is logarithmic in the size of their interest set.

A Personalized Approach for Re-ranking Search Results Using User Preferences

Web search engines provide users with a huge number of results for a submitted query. However, not all returned results are relevant to the user's needs. Personalized search aims at solving this problem by modeling search interests of the user in a profile and exploiting it to improve the search process. One of the challenges in search personalization is how to properly model user's search interests. Another challenge is how to effectively exploit these models to enhance the search quality. In this paper, an effective hybrid personalized re-ranking search approach is proposed by modeling user's search interests in a conceptual user profile, and then exploiting this profile in the re-ranking process. The user profile consists of concepts obtained by hierarchically classifying user's clicked search results into categories. These categories are extracted from the taxonomy of concepts called The Open Directory Project (ODP) where each concept represents a category. Additionally, each concept in the user profile consists of two types of documents; taxonomy document and viewed document. Taxonomy document is used to represent the user general interests as it contains information from web pages originally associated with such ODP category. Viewed document is used to represent the user specific interests as it contains information from web pages clicked by the user. Finally, the re-ranking process of search results is performed by semantically integrating user's general and specific interests from the user profile together with rankings of the traditional search engine. Experimental results show that semantic identification of user's search interests improves re-ranking quality by providing users with the most relevant results at the top of the search results list.

A multilevel approach to intelligent information filtering

In information-filtering environments, uncertainties associated with changing interests of the user and the dynamic document stream must be handled efficiently. In this article, a filtering model is proposed that decomposes the overall task into subsystem functionalities and highlights the need for multiple adaptation techniques to cope with uncertainties. A filtering system, SIFTER, has been implemented based on the model, using established techniques in information retrieval and artificial intelligence. These techniques include document representation by a vector-space model, document classification by unsupervised learning, and user modeling by reinforcement learning. The system can filter information based on content and a user's specific interests. The user's interests are automatically learned with only limited user intervention in the form of optional relevance feedback for documents. We also describe experimental studies conducted with SIFTER to filter computer and information science documents collected from the Internet and commercial database services. The experimental results demonstrate that the system performs very well in filtering documents in a realistic problem setting.