2019-05-13

1. The richness of CMC has brought about the emergence of many types of CMC text analysis.

2. These include analysis of participation levels, interaction, social cues, topics, user roles, linguistic variation, types of questions posed, and response complexity

3. The features (i.e., attributes) utilized for CMC text analysis can be broadly categorized as either structural or text-based.

4. Structural features are attributes based on communication topology.

5. These features are extracted solely from message headers, without any use of information contained in the message body

6. Structural features support activity and interaction analysis.

7. Posting activity related features include number of posts, number of initial messages, number of replies, and number of responses to a particular author's posts

8. These features can be used to represent an authors' social accounting metrics

9. Analysis of activity based attributes also provides insight into different roles played by online community members, such as debaters, experts, and disseminators

10. Features used for interaction analysis include the frequency of incoming and outgoing messages.

11. These features are used as input for the construction of social networks based on who is talking to whom

12. Text features are attributes derived from the message body.

13. Although the informational richness of CMC text was previously questioned (Daft and Lengel 1986), numerous studies have since demonstrated the opulence /ˈɒpjʊləns/ (财富) of CMC text

14. In addition to topical information, CMC text is rich in social cues (Henri 1992), power cues (Panteli 2002), and genres (Yates and Orlikowski 2002).

15. Social cues are elements not related to formal content or subject matter (Henri 1992).

16. Examples include self-introductions, expressions of feelings, greetings, signatures, jokes, use of symbolic icons, and compliments

17. CMC text also contains evidence of power cues; stylistic indicators of one's position/ rank within an organization or online community

18. Genres are types of writing based on purpose and form (e.g., memos, meetings, reports, etc.).

19. Highly prevalent in CMC, they serve as sources of organizing structures and communicative norms

20. Inclusion of structural and text-based features is critical for CMC text analysis.

21. For instance, online community sustain ability analysis requires the use of communication activity, interaction, and text content attributes

22. Similarly, Cothrel (2000) incorporated structural features (activity measures) and text features (discussion topics) into his model for measuring an online community's return on investment.

23. He noted that activity measures describe the general health of a community while discussion topic metrics "assess the ongoing insights that the community offers into the business's products or processes"

24. CMC systems can be sorted into two categories based on functionality: those that support the communication process and those that support analysis of communication content (Sack 2000).

25. While it is certainly possible for a single system to support both functions (e.g., Erickson and Kellogg 2000), we focus only on the analysis functionalities provided by these systems due to their relevance to CMC text analysis.

26. Table 1 provides a review of prior CMC systems supporting analysis of text-based CMC.

27. The review is based on the analysis features incorporated by these systems.

28. A plethora /ˈplɛθ(ə)rə/ of CMC systems have been developed to support structural features.

A large or excessive amount of something.

29. Several tools visualize posting activity patterns, such as Loom (Donath et al. 1999) and Authorlines (Viegas and Smith 2004).

30. PeopleGarden and Communication Garden both use garden metaphors（ˈmetəfə(r)暗喻） with flower glyphs [ɡlɪf] to display author and thread activity

A hieroglyphic character or symbol.

31. The number of petals（花瓣） and thorns（棘刺）, petal colors, and stem lengths are used to represent activity features such as the total number of posts and number of threads in which an author has participated.

32. Babble (Erickson and Kellogg 2000) and Coterie (Donath 2002) are both geared toward showing activity patterns in persistent conversation.

Gear towards：to design or organize something so that it is suitable for a particular purpose, situation, or group of people:

33. In these systems, all participants are displayed in a two-dimensional space.

34. More active authors are shown in the center while participants with fewer postings gradually shift to the perimeter.

35. The visual effect is a good method for identifying active participants versus lurkers

36. Systems displaying interaction information also exist.

37. Conversation Map visualizes social networks based on send/ reply patterns

38. NetScan displays message and author interactions (Smith and Fiore 2001), while Loom shows thread-level interaction structures (Donath et al. 1999).

39. Previous CMC systems offer limited support for text-based features.

40. Loom shows some content patterns based on message moods.

41. Moods are assigned by taking into consideration the occurrence of certain terms and punctuation in the message text.

42. Chat Circles displays messages based on body text length.

43. Conversation Map and Communication Garden provide more in-depth topical analysis.

44. Conversation Map uses computational linguistics to build semantic networks for discussion topics while Communication Garden performs topic categorization using noun phrases.

45. Text systems are a related class of systems that are used for either information retrieval (IR systems) or general text categorization and analysis (text mining systems).

46. However, IR systems are more concerned with information access than analysis

47. Mladenic (1999) presented a review of 29 IR systems, all of which used bag-of-words to represent text document topics.

48. Similarly, Tan (1999) reviewed 11 commercial text mining systems and found IBM's Intelligent Miner to be the most comprehensive.

49. However, this system also utilizes limited feature representations (i.e., bag-of words, named entities) and only performs topic categorization and analysis (Dorre et al. 1999).

50. Overall, the features used in existing CMC text analysis systems are insufficient to effectively capture text-based content in CMC

51. Paccagnella suggested that computer programs to support CMC text analysis would be helpful, yet do not exist.

52. He noted numerous ways in which automated systems could benefit CMC text analysis, including data linking, content analysis, data display, and graphic mapping.

53. Without appropriate CMC text analysis systems, text features are often overlooked (Panteli 2002).

54. There has been limited analysis of CMC text since manual methods are time consuming

55. Cothrel (2000) stated that discussion content is an essential dimension of online community success measurement, yet proper definition and measurement remains elusive.