CNAVER: A Content and Network-based Academic VEnue Recommender system

Pradhan, Tribikram; Pal, Sukomal

doi:10.1016/j.knosys.2019.105092

Cited by 32 publications

(17 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Medvet, Bartoli, and Piccinin [9] test three different methods based on n-grams and Latent Dirichlet Allocation. More complex, hybrid methods integrate social network analysis [14,13]. All of the above do not add explanations to recommendations.…”

Section: Related Workmentioning

confidence: 99%

“…To support researchers with this task, different methods have been proposed, e.g., based on Latent Dirichlet Allocation [9], hybrid approaches incorporating social networks [14,13], or procedures that draw from background ontologies [20,16]. Moreover, recent approaches based on deep learning methods achieved high accuracy in recommendations [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Explainable Scientific Venue Recommendations

Schäfermeier,

Stumme,

Hanika

2021

Preprint

View full text Add to dashboard Cite

Selecting the best scientific venue (i.e., conference/journal) for the submission of a research article constitutes a multifaceted challenge. Important aspects to consider are the suitability of research topics, a venue's prestige, and the probability of acceptance. The selection problem is exacerbated through the continuous emergence of additional venues. Previously proposed approaches for supporting authors in this process rely on complex recommender systems, e.g., based on Word2Vec or TextCNN. These, however, often elude an explanation for their recommendations. In this work, we propose an unsophisticated method that advances the state-of-the-art in two aspects: First, we enhance the interpretability of recommendations through non-negative matrix factorization based topic models; Second, we surprisingly can obtain competitive recommendation performance while using simpler learning methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards Explainable Scientific Venue Recommendations

Schäfermeier,

Stumme,

Hanika

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In contrast, models proposed by Pan et al [10] or Rollins et al [11] utilise explicit feature engineering to include clues about citation or authors networks. Pradhan et al [18] recommend venues by enhancing the representations of a paper's title and abstract with meta-path features extracted from citation and bibliographic networks. Küc ¸üktunc ¸et al [19] and Boukhris and Ayachi [20] generate recommendations without considering the content of a prospective manuscript by extending bibliographic data with citation relationships.…”

Section: Related Workmentioning

confidence: 99%

“…Continuously crawling WikiCfP for information about future conferences could ensure that users are always provided with up-to-date information about the recommended conferences. Moreover, providing more comprehensive ratings of all the suggested conferences and incorporating different rankings, such as CORE 18 , could provide an objective measure of distinguishing between numerous conferences from different tiers. However, removing niche conferences or workshops from the recommendation list could reduce the diversity of results.…”

Section: Fine-tuning Recommendations Based On Additional Featuresmentioning

confidence: 99%

GraphConfRec: A Graph Neural Network-Based Conference Recommender System

Iana

Paulheim

2021

2021 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

View full text Add to dashboard Cite

In today's academic publishing model, especially in Computer Science, conferences commonly constitute the main platforms for releasing the latest peer-reviewed advancements in their respective fields. However, choosing a suitable academic venue for publishing one's research can represent a challenging task considering the plethora of available conferences, particularly for those at the start of their academic careers, or for those seeking to publish outside of their usual domain. In this paper, we propose GraphConfRec, a conference recommender system which combines SciGraph and graph neural networks, to infer suggestions based not only on title and abstract, but also on coauthorship and citation relationships. GraphConfRec achieves a recall@10 of up to 0.580 and a MAP of up to 0.336 with a graph attention network-based recommendation model. A user study with 25 subjects supports the positive results.

show abstract

“…Another work focused on the academic area is [Pradhan and Pal 2020], that propose CNAVER, a content-based and network-based SR for recommending vehicles for publications. The researchers state that this type of recommendation can help find places more related to the publication to be made, improving the impact and avoiding rejection of good articles due to lack of alignment with the publication vehicle.…”

Section: Related Workmentioning

confidence: 99%

Combining Clustering and Regression Models for Recommending Researchers

Lima

Oliveira

2021

Anais Do IX Symposium on Knowledge Discovery, Mining and Learning (KDMiLe 2021)

View full text Add to dashboard Cite

Due to the increase in scientific production, especially in recent years, management and decision support challenge also increase significantly. The task of recommending researchers, for example, to a project is not simple. Even with the proper amount of data, ranking and recommending researchers becomes a challenging process. Despite the different methods, what can happen is that the datasets of an institution or research areas do not have a ranking value, that is, a value that can be used to assess the position of a researcher. Even having a necessary dataset, there is no ranking information for these researchers, and this process of obtaining data for training a model can be costly. We propose to use clustering techniques to support the ranking process, reducing the human effort to obtain examples for models training. Then, we used this dataset to train the regression models and Mean Squared Error (MSE) and Normalized Discounted Cumulative Gain (nDCG) to evaluate them. Tests demonstrate that our solution can support the researchers' recommendation process in an adaptive process to the needs of an organization.

show abstract

CNAVER: A Content and Network-based Academic VEnue Recommender system

Cited by 32 publications

References 43 publications

Towards Explainable Scientific Venue Recommendations

Towards Explainable Scientific Venue Recommendations

GraphConfRec: A Graph Neural Network-Based Conference Recommender System

Combining Clustering and Regression Models for Recommending Researchers

Contact Info

Product

Resources

About