Discovery of Topical Authorities in Instagram

@article{Pal2016DiscoveryOT,
  title={Discovery of Topical Authorities in Instagram},
  author={Aditya Pal and Amac Herdagdelen and Sourav Chatterji and Sumit Taank and Deepayan Chakrabarti},
  journal={Proceedings of the 25th International Conference on World Wide Web},
  year={2016}
}
Instagram has more than 400 million monthly active accounts who share more than 80 million pictures and videos daily. This large volume of user-generated content is the application's notable strength, but also makes the problem of finding the authoritative users for a given topic challenging. Discovering topical authorities can be useful for providing relevant recommendations to the users. In addition, it can aid in building a catalog of topics and top topical authorities in order to engage new… 

Figures and Tables from this paper

Expertise-aware news feed updates recommendation: a random forest approach

Following extensive experiments on a real dataset crawled from Twitter, the results show that infer the author’s expertise is critical for identifying relevant updates in news feeds.

Expertise-aware news feed updates recommendation: a random forest approach

Following extensive experiments on a real dataset crawled from Twitter, the results show that infer the author’s expertise is critical for identifying relevant updates in news feeds.

TAGme: A Topical Folksonomy Based Collaborative Filtering for Tag Recommendation in Community Sites

The experimental results demonstrate that the proposed TAGme algorithm performs better in comparison to the other tag recommendation algorithm, and is carried with standard tag recommendation algorithms, namely, TF, TF-IDF, LDA, tag-LDA, RTM and MAT.

Inferring your expertise from Twitter: combining multiple types of user activity

A learning model that tries to infer a user's topical expertise from Twitter using information such as tweets posted by the user and the characteristics of their followers, which outperforms several baseline approaches and outperforms approaches which use only a single type of user data for inference.

Evaluation of Graph-based Algorithms for Guessing User Recommendations of the Social Network Instagram

This paper builds a neighborhood graph for selected active users on Instagram, and shows that an algorithm based on Twitter's Who-to-Follow algorithm is most similar to Instagram's unknown algorithm when recommending users connected to the followees of the target users.

Personalized Topic Graph Generation Method Using Image Labels in Image-Sharing SNS

A modified Latent Dirichlet Allocation (LDA) model named LDA-IL is proposed that utilizes relatively low-noise image data compared with text documents and a method of generating the personalized topic graph that represents the users’ interests is proposed.

Topic trends and user engagement on Instagram

Analysis of a large-scale dataset of public posts from influencer profiles on Instagram revealed that both kinds of features are relevant to predicting the success of a post, and the results differ according to the size of the follower base of the influencers.

Institutional Knowledge at Singapore Management University On analyzing user topic-specific platform preferences across multiple social media sites

The experiments results show that the MultiLDA outperforms in both topic modeling and platform choice prediction tasks, and it is shown empirically that among the three social media platforms, “ Daily matters” and “ Relationship matters ” are dominant topics in Twitter.

References

SHOWING 1-10 OF 43 REFERENCES

Identifying topical authorities in microblogs

This work proposes a set of features for characterizing social media authors, including both nodal and topical metrics, and shows how probabilistic clustering over this feature space, followed by a within-cluster ranking procedure, can yield a final list of top authors for a given topic.

Cognos: crowdsourcing search for topic experts in microblogs

This paper proposes and investigates a new methodology for discovering topic experts in the popular Twitter social network that leverages Twitter Lists, which is often carefully curated by individual users to include experts on topics that interest them and whose meta-data provides valuable semantic cues to the experts' domain of expertise.

Discovering authorities in question answer communities by using link analysis

An analysis of the link structure of a general-purpose question answering community to discover authoritative users is presented, and promising experimental results over a dataset of more than 3 million answers from a popular community QA site are described.

Robust Entity Linking via Random Walks

This work adopts a unified semantic representation for entities and documents - the probability distribution obtained from a random walk on a subgraph of the knowledge base - which can overcome the feature sparsity issue that affects previous work.

Finding high-quality content in social media

This paper introduces a general classification framework for combining the evidence from different sources of information, that can be tuned automatically for a given social media type and quality definition, and shows that its system is able to separate high-quality items from the rest with an accuracy close to that of humans.

You Are Who You Talk To: Detecting Roles in Usenet Newsgroups

A method of applying social network analysis to support the task of characterizing authors in Usenet newsgroups is presented and it is found that second-degree ego-centric networks give us clear distinctions between different types of authors and newsgroups.

User Interest and Topic Detection for Personalized Recommendation

A novel graphical model is proposed to extract hidden topics from web contents, clusterweb contents, and detect users' interests on each cluster, and two reranking models are introduced which utilize the detected user interest to further boost the quality of personalized recommendation.

Formal models for expert finding in enterprise corpora

This work presents two general strategies to expert searching given a document collection which are formalized using generative probabilistic models, and shows that the second strategy consistently outperforms the first.

Link analysis ranking: algorithms, theory, and experiments

This article works within the hubs and authorities framework defined by Kleinberg and proposes new families of algorithms, and provides an axiomatic characterization of the INDEGREE heuristic which ranks each node according to the number of incoming links.

Discovering Experts across Multiple Domains

An expertise framework that aims at extracting key expertise features and building an unified scoring model based on SVM ranking algorithm is proposed and it is shown that it is significantly better than the prior state-of-art.