Discovering activity transition patterns in social media check-in behavior via temporal activity motifs

Abstract

Location-Based Social Network (LBSN) has produced a large quantity of user check-in data. A profound understanding of user behavior and intrinsic needs can be achieved by identifying patterns in activity type transitions, thereby enabling more intelligent location-based services. We proposed temporal activity motif and used this structure to identify frequent activity type transition patterns from check-in sequences, discovering the relationship and interaction between different activity types. 383 temporal activity motifs of 17 temporal topologies were extracted from the two-year Gowalla dataset of New York-Newark-Jersey City, NY-NJ-PA Metropolitan Statistical Area (MSA). These motifs are categorized into two groups: one is sequential motifs representing a complete activity process, while the other is non-sequential motifs representing the co-occurrence of two separate processes. They provide evidence of activity type recurrence, particularly in longer activity processes, highlights the cyclical nature of human mobility. Additionally, various activity types exhibit different influences on others and occupy different positions in activity processes. Furthermore, by leveraging non-sequential motifs, we specifically uncovered the co-occurrence patterns between two separate activity process. These findings bring new insights to optimize recommendation system and urban planning.

Keywords: Activity sequence; Activity type transition; Check-in data; Location-based social network; Temporal activity motif; Temporal motif.

Fig. 1

Temporal activity motif and its two key features.

Fig. 2

The schematic diagrams of 17 temporal topologies and the number of their occurrences in the dataset (i.e., the number of activity sequences containing them).

Fig. 3

The activity type distributions in Line (a), Ring (b), and Triple_line (c) motifs. The distribution of activity type transitions is shown in the heat map, where rows represent types of node A and columns represent types of node B. The type distributions of each single node are shown in bar charts on the left side and top of the heat maps.

Fig. 4

The activity type distributions in Chain (a, b), Triad (c, d), Star_pre (e, f), and Star_pos (g, h) motifs. The distributions of activity type transitions are shown in a series of grouped pie charts in (a, c, e, g), where rows represent types of node B, columns represent types of node C, colors of the pie represent types of node A, and pie sizes represent numbers of occurrence of specific motifs in dataset. The type distributions of nodes A to C are shown in bar charts in (b, d, f, h).

Fig. 5

The Cumulative Occurrence Ratio of motifs with different typical travel demands in three-node temporal topologies (Chain, Star_pre, Star_pos, and Triad).

Fig. 6

Schematic diagrams of nine Triple_chain motifs.

Fig. 7

The activity type distribution of transitions of two-edge non-sequential motifs. High values are labeled with lowercase letters, with ‘a’ representing the number of occurrences greater than 500, ‘b’ between 400 and 500, ‘c’ between 300 and 400, and ‘d’ between 200 and 300. Each row represents a type of transition A→B, and each column represents a type of transition C→D. Node B is the end of the previous process, and node C is the beginning of the subsequent process. They form the bridging mode in non-sequential motifs. Motifs within the same large grid share a bridging pattern, meaning the types of B and C are identical.

Fig. 8

Methodological framework of the study.