Visualizing the impact of time series data for predicting user interactions

Macek, Bjoern-Elmar; Atzmueller, Martin

doi:10.1145/2492517.2492601

Cited by 4 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be observed within the plot, as the probability of an example to belong to the negative class is the largest in the origin and decreases with increasing feature values for b7 and b8. This observation is also supported by [16].…”

Section: Overviewsupporting

confidence: 75%

“…In this work, we will utilize a more generic set of time series features which can capture this and other similar temporal patterns. We demonstrated the impact of those features in the task of predicting userinteractions in [16]. There is already a wide range of approaches, which are used to classify time series data.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, in contrast to [20], for instance, we use a different and more generic set of time series features, that is able to capture a wide range of temporal patterns in the model training process. Some of those patterns are described in [16]. Similar feature sets have been successfully used for time series probability forecasting, e. g., [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting the stability of user interaction ties in Twitter

Macek

Atzmueller

Stumme

2014

Proceedings of the 14th International Conference on Knowledge Technologies and Data-Driven Business

Self Cite

View full text Add to dashboard Cite

In this paper, we analyze the stability of user interaction within Twitter focusing on link decay prediction: for a tweet created by one user mentioning another user we study the task of predicting the decay of the corresponding interaction link over time. For this task, we employ the history of timestamped mention interactions between both users as time series features. We also tackle the problem of efficiently balancing a large dataset with a skewed class distribution, which arises naturally in our context. The proposed impurity-based supervised sampling (ISS) approach balances the data in one pass by removing trivial training data of the overrepresented class. Our approach is evaluated using the well known Twitter dump of 2009 [25]. We show, that ISS outperforms downsampling with regard to the resulting predictor performance.

show abstract

Section: Overviewsupporting

confidence: 75%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the stability of user interaction ties in Twitter

Macek

Atzmueller

Stumme

2014

Proceedings of the 14th International Conference on Knowledge Technologies and Data-Driven Business

Self Cite

View full text Add to dashboard Cite

show abstract

“…Rojas and Villegas presented an approach of representation and scheme of investigative visualization for the decision tree in the knowledge discovery database process for data mining [19]. Macek and Atzmueller [20] presented a new concept of visualization for the user history interactions. Association rules are derived and visualized through heatmaps.…”

Section: Related Workmentioning

confidence: 99%

User Knowledge, Data Modelling, and Visualization: Handling through the Fuzzy Logic‐Based Approach

Liao

Nazir

Zhou³

et al. 2021

Complexity

View full text Add to dashboard Cite

In modern day technology, the level of knowledge is increasing day by day. This increase is in terms of volume, velocity, and variety. Understanding of such knowledge is a dire need of an individual to extract meaningful insight from it. With the advancement in computer and image-based technologies, visualization becomes one of the most significant platforms to extract, interpret, and communicate information. In data modelling, visualization is the process of extracting knowledge to reveal the detail data structure and process of data. The proposed study aim is to know about the user knowledge, data modelling, and visualization by handling through the fuzzy logic-based approach. The experimental setup is validated through the data user modelling dataset available in the UCI web repository. The results show that the model is effective and efficient in situations where uncertainty and complexity arise.

show abstract